Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Xiaokang YangSuggested from co-authorship
- Ke GuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works417 from public data
- Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels664
The proposed Q-Align achieves state-of-the-art performance on image quality assessment (IQA), image aesthetic assessment (IAA), as well as video quality assessment (VQA) tasks under the original LMM structure and unify the three tasks into one model, termed the OneAlign.
- Perceptual image quality assessment: a survey660
This survey provides a general overview of classical algorithms and recent progresses in the field of perceptual image quality assessment and describes the performances of the state-of-the-art quality measures for visual signals.
- 515
- 454
- Unified Blind Quality Assessment of Compressed Natural, Graphic, and Screen Content Images340
A unified content-type adaptive (UCA) blind image quality assessment model that is applicable across content types and leads to superior performance on the constructed CCT database, and is training-free, implying strong generalizability.
- 328
- A Deep Learning based No-reference Quality Assessment Model for UGC Videos308
A very simple but effective UGC VQA model is proposed, which tries to address this problem by training an end-to-end spatial feature extraction network to directly learn the quality-aware spatial feature representation from raw pixels of the video frames.
- 296
- 273
- AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment263
This work extensively considers various popular AGI models, generated AGI through different prompts and model parameters, and collected subjective scores at the perceptual quality and text-to-image alignment, thus building the most comprehensive AGI subjective quality database AGIQA-3K so far.
- 256
- Screen Content Quality Assessment: Overview, Benchmark, and Beyond250
The background, history, recent progress, and future of the emerging screen content quality assessment research are provided, including an overview of the most technology-oriented part of QoE modeling.
- 240
- 226
- Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training213
A novel BIQA model for in-the-wild images is proposed by addressing two critical problems in this field: how to learn better quality-aware feature representation, and how to solve the problem of insufficient training samples in terms of their content and distortion diversity.
- 213
- Perceptual video quality assessment: a survey211
This survey provides a systematic overview of both classical works and recent progress in the realm of video quality assessment, which can help other researchers quickly access the field and conduct relevant research.
- No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models194
A no-reference (NR) quality assessment metric for colored 3D models represented by both point cloud and mesh is proposed and greatly reduces the performance gap with the state-of-the-art FR 3D-QA metrics.
- Perceptual Quality Assessment of Omnidirectional Images171
A perceptual omnidirectional image quality assessment (IQA) study since it is extremely important to provide a good quality of experience under the VR environment, and some new observations different from traditional IQA are made.
- 169
- 158
- The prediction of head and eye movement for 360 degree images140
This paper studies the problem of predicting head movement, head–eye motion, and scanpath of viewers when they are watching 360 degree images in the commodity HMDs and designs a model to predict the saliency maps for the first two, and the scanpaths for the last one.
- Attention-Guided Neural Networks for Full-Reference and No-Reference Audio-Visual Quality Assessment126
- A Perceptual Quality Assessment Exploration for AIGC Images122
The first perceptual AGI quality assessment database, AGIQA-1K, which consists of 1,080 AGIs generated from diffusion models is presented and a benchmark experiment is conducted to evaluate the performance of current image quality assessment (IQA) models.
- A dataset of eye movements for the children with autism spectrum disorder120
Based on this dataset, researchers could analyze the visual traits of children with ASD and design specialized visual attention models to promote research in related fields, as well as design specialized models to identify the individuals with ASD.
- 118
- Exploring Rich Subjective Quality Information for Image Quality Assessment in the Wild114
RichIQA outperforms state-of-the-art competitors on multiple large-scale in the wild IQA databases with rich subjective rating labels and can fully exploit the potentials within subjective quality rating and enhance the prediction performance and generalizability of the network.
- Blurry Video Frame Interpolation111
A pyramid module to cyclically synthesize clear intermediate frames to reduce motion blur and up-convert frame rate simultaneously is developed and an inter-pyramid recurrent module is proposed to connect sequential models to exploit the temporal relationship.
- Evaluating Quality of Screen Content Images Via Structural Variation Analysis110
This paper separates structures into global and local structures, which correspond to basic and detailed perceptions of humans, respectively, and systematically combines the measurements of variations in the above-stated two types of structures to yield the final quality estimation of screen content images.
- 108
- 107
- End-to-End Human-Gaze-Target Detection with Transformers96
Unlike existing two-stage methods that require human head locations as input and can predict only one human's gaze target at a time, HGTTR can directly predict the locations of all people and their gaze targets at one time in an end-to-end manner.
- 93
- Perceptual Quality Assessment of Low-light Image Enhancement88
This article proposes a new FR low-light image enhancement quality assessment (LIEQA) index by evaluating the image quality from four aspects: luminance enhancement, color rendition, noise evaluation, and structure preserving, which have captured the most key aspects of low-lights enhancement.
- 86
- Confusing Image Quality Assessment: Toward Better Augmented Reality Experience84
This paper considers AR technology as the superimposition of virtual scenes and real scenes, and introduces visual confusion as its basic theory, and establishes an ARIQA database to better simulate the real AR application scenarios.
- GMS-3DQA: Projection-Based Grid Mini-patch Sampling for 3D Model Quality Assessment78
The experimental results show that the proposed GMS-3DQA outperforms existing state-of-the-art NR-3DQA methods on the point cloud quality assessment databases for both accuracy and efficiency.
- MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos77
A Multi-12imensional VQA (MD-VQA) evaluator is developed to measure the visual quality of UGC live videos from semantic, distortion, and motion aspects respectively and achieves state-of-the-art performance on both the UGC Live V QA database and existing compressed UGC VQ a databases.
- Saliency-induced reduced-reference quality index for natural scene and screen content images77
Experimental results show that SIRR is comparable to state-of-the-art full-reference and reduced-reference IQA measures in NSIs, and it can outperform most competitors in SCIs.
- Deep Learning Based Full-Reference and No-Reference Quality Assessment Models for Compressed UGC Videos76
The proposed deep learning based video quality assessment (VQA) framework achieves the best performance among the stateof-the-art FR and NR V QA models on the Compressed UGC VQA database and also achieves pretty good performance on the in- the-wild UGC vQA databases.
- A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequences73
The experimental results show that the proposed no-reference quality assessment metric for colored point cloud outperforms most of the state-of-the-art full-reference and no- reference PCQA metrics, which validates the effectiveness of the proposed method.
- 72
- Evaluating Point Cloud From Moving Camera Videos: A No-Reference Metric69
The experimental results reveal that the proposed VQA method is effective for predicting the visual quality levels of the point clouds and even competitive with full-reference (FR) PCQA methods.
- Assessment of eye fatigue caused by head-mounted displays using eye-tracking67
This work proposed a novel computational approach for estimation of eye fatigue by providing various verifiable models and presented a new scheme to assess eye fatigue of HMDs users by analysis of parameters of the eye tracker.
- 65
- AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment65
The largest fine-grained AIGI subjective quality database to date with 20,000 AIGIs and 420,000 subjective ratings, known as AIGIQA-20K is released and it is anticipated that this large-scale quality database will inspire robust quality indicators for AIGIs and propel the evolution of AIGC for vision.
- 65
- Image Quality Assessment: From Mean Opinion Score to Opinion Score Distribution63
A convolutional neural network based on fuzzy theory is proposed to predict the opinion score distribution of image quality by learning the mapping from epistemic uncertainty to the uncertainty existing in the image quality ratings.
- Deep Neural Network for Blind Visual Quality Assessment of 4K Content63
A deep learning-based BIQA model is proposed, aiming to recognize true and pseudo 4K content and meanwhile evaluate their visual quality, and the experimental results show that the proposed model outperforms all compared BIZA metrics on four 4Kcontent quality assessment databases.
- Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models62
A first-of-its-kind computational analysis of VQA datasets via designing minimalistic BVQA models that cast doubt on the current progress in BVQA, and shed light on good practices of constructing next-generation VQA datasets and models.
- Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment60
This work proposes a novel transformer-based model for subjective-aligned Text-to-Video Quality Assessment (T2VQA), which extracts features from text-video alignment and video fidelity perspectives, then it leverages the ability of a large language model to give the prediction score.
- Large multimodal models evaluation: a survey57
By unifying general-specialized understanding and modality-specific generation evaluations, this survey clarifies the current landscape and provides guidance for future research in the LMM evaluation field.
- LMM-PCQA: Assisting Point Cloud Quality Assessment with LMM55
This study investigates the feasibility of imparting PCQA knowledge to LMMs through text supervision, and transforms quality labels into textual descriptions during the fine-tuning phase, enabling LMMs to derive quality rating logits from 2D projections of point clouds.
- Visual Attention Analysis and Prediction on Human Faces for Children with Autism Spectrum Disorder55
The proposed model shows the best performance among all competitors and could be used to design specialized education contents containing human faces for the children with ASD or produce the specific model for rapidly screening ASD using their eye movement data.
- A-Bench: Are LMMs Masters at Evaluating AI-generated Images?54
This paper introduces A-Bench, a benchmark designed to diagnose whether LMMs are masters at evaluating AIGIs, and organizes various generative models utilized for AIGI creation, and various LMMs employed for evaluation, which ensures a comprehensive validation scope.
- NTIRE 2024 Quality Assessment of AI-Generated Content Challenge54
This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC).
- FineVQ: Fine-Grained User Generated Content Video Quality Assessment53
The first large-scale Fine-grained Video quality assessment Database is established, termed FineVD, which comprises 6104 UGC videos with fine-grained quality scores and descriptions across multiple dimensions, and a Fine-grained Video Quality assessment (FineVQ) model is proposed to learn the fine-grained quality of UGC videos.
- Large Multi-modality Model Assisted AI-Generated Image Quality Assessment53
A large Multi-modality model Assisted AI-Generated Image Quality Assessment (MA-AGIQA) model is introduced, which utilizes semantically informed guidance to sense semantic information and extract semantic vectors through carefully designed text prompts and employs a mixture of experts (MoE) structure to dynamically integrate the semantic information with the quality-aware features extracted by traditional DNN-based IQA models.
- 53
- Implicit Neural Representation Learning for Hyperspectral Image Super-Resolution52
This work proposes a novel HSI reconstruction model based on INR which represents HSI by a continuous function mapping a spatial coordinate to its corresponding spectral radiance values in a content-aware manner.
- 51
- 51
- Advancing Zero-Shot Digital Human Quality Assessment Through Text-Prompted Evaluation50
A zero-shot DHQA approach that focuses on no-reference scenarios to ensure generalization capabilities while mitigating database bias is proposed and the Digital Human Quality Index (DHQI) is introduced, which demonstrates significant improvements in zero-shot performance.
- 50
- 50
- 49
- Q-Bench-Video: Benchmark the Video Quality Understanding of LMMs47
Q-Bench-Video is introduced, a new benchmark specifically designed to evaluate LMMs' proficiency in discerning video quality, and indicates that while LMMs have a foundational understanding of perceptual video quality, their performance remains incomplete and imprecise, with a notable discrepancy compared to the performance of human beings.
- 47
- AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM46
A novel VQA model that leverages spatiotemporal features and LMM frameworks to capture the intricate quality attributes of AIGVs, thereby accurately predicting precise video quality scores and video pair preferences is introduced and demonstrates state-of-the-art performance.
- 46
- 46
- 46
- LMM-VQA: Advancing Video Quality Assessment With Large Multimodal Models44
An Large Multi-Modal based Video Quality Assessment (LMM-VQA) model is proposed, which introduces a novel spatiotemporal visual modeling strategy for quality-aware feature extraction and achieves state-of-the-art performance across five VQA benchmarks.
- 44
- Quality Assessment for AI Generated Images With Instruction Tuning43
The proposed MINT-IQA model achieves state-of-the-art performance in understanding and evaluating human visual preferences for AIGIs, and the proposed model also achieves competing results on traditional IQA tasks compared with state-of-the-art IQA models.
- 43
- Toward Visual Behavior and Attention Understanding for Augmented 360 Degree Videos43
To bridge the gap between the saliency prediction on real-world scenes and on scenes augmented by virtual information, the ARVR saliency dataset is constructed and a model that is capable of solving theSaliency prediction problem in AR is designed.
- Self-Conditioned Probabilistic Learning of Video Rescaling43
A self-conditioned probabilistic framework for video rescaling to learn the paired downscaling and upscaling procedures simultaneously, and extends the framework to a lossy video compression system, in which a gradient estimator for non-differential industrial lossy codecs is proposed for the end-to-end training of the whole system.
- LMM4LMM: Benchmarking and Evaluating Large-Multimodal Image Generation With LMMs42
Extensive experimental results show that LMM4LMM achieves state-of-the-art performance on EvalMi-50K, and exhibits strong generalization ability on other AI-generated image evaluation benchmark datasets, manifesting the generality of both the EvalMi-50K dataset and LMM4LMM metric.
- 42
- Saliency in Augmented Reality42
To better predict the saliency in AR, a vector quantized saliency prediction method is proposed and generalize it for ARSaliency prediction, and experimental results demonstrate the superiority of the proposed method on both of the common saliency predictions problem and the AR saliency Prediction problem over benchmark methods.
- Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content41
Experimental results indicate that the proposed Q-Eval-Score achieves superior performance on both visual quality and alignment, with strong generalization capabilities across other benchmarks, highlighting the significant value of the Q-EVAL-100K dataset.
- 41
- Video Quality Assessment: A Comprehensive Survey40
A comprehensive survey of recent progress in the development of VQA algorithms and the benchmarking studies and databases that make them possible is presented and open research directions on study design and VQA algorithm architectures are analyzed.
- Free-energy principle inspired visual quality assessment: An overview40
The free energy principle inspired visual quality assessment metrics with a comparison in terms of algorithm design and performance are reviewed.
- 39
- QoE Driven VR 360° Video Massive MIMO Transmission39
This paper forms an integer non-linear programming (INLP) problem to maximize users’ average quality of experience (QoE) score, and transforms the original INLP problem into an integer linear programming problem by setting the predictive tiles groups as some constants.
- 39
- 38
- 38
- 38
- Subjective and Objective Quality Assessment for in-the-Wild Computer Graphics Images37
An effective deep learning–based no-reference no-reference IQA model is proposed by utilizing both distortion and aesthetic quality representation and outperforms all other state-of-the-art NR IQA methods on the constructed CGIQA-6k database and other CGIQA-related databases.
- Utility-oriented resource allocation for 360-degree video transmission over heterogeneous networks37
An application-layer scheme to jointly exploit the available bandwidth from the LTE and Wi-Fi networks in 360-degree video streaming and a novel buffer strategy is proposed to mitigate the influence of short-time prediction problem for transmitting360-degree videos in time-varying networks.
- R-Bench: Are Your Large Multimodal Model Robust to Real-World Corruptions?36
R-Bench is introduced, a benchmark focused on the Real-world Robustness of LMMs, and shows that while LMMs can correctly handle the original reference images, their performance is not stable when faced with distorted images, and there is a significant gap in robustness compared to the human visual system.
- 36
- Visual attention analysis and prediction on human faces36
This work proposes to build visual attention models specifically for face images through combining low-level saliency calculated by traditional saliency models with high-level facial features, and efficiency of the built models is verified on the VAF database.
- 35
- Eye Fatigue Assessment Using Unobtrusive Eye Tracker35
Two real-time eye fatigue assessment models are proposed based on eye movement data and eye blink data, respectively and can provide an accurate eye fatigue level to users.
- 34
- VQA 2 : Visual Question Answering for Video Quality Assessment33
This work provides a foundation and feasible approach for integrating low-level video quality assessment and understanding with LMMs, and presents the VQA² series models, which exceeds the renowned GPT-4o in visual quality understanding tasks while maintaining strong competitiveness in quality scoring tasks.
- Perceptual Quality Assessment for Digital Human Heads33
The first large-scale quality assessment database for three-dimensional (3D) scanned digital human heads (DHHs) and a simple yet effective full-reference (FR) projection-based method is proposed to evaluate the visual quality of DHHs.
- 33
- 33
- StableVQA: A Deep No-Reference Quality Assessment Model for Video Stability31
A new database named StableDB is built that contains 1,952 diversely-shaky UGC videos, where each video has a Mean Opinion Score on the degree of video stability rated by 34 subjects and a novel VQA-S model named St stableVQA, which consists of three feature extractors to acquire the optical flow, semantic, and blur features respectively, and a regression layer to predict the final stability score.
- VDPVE: VQA Dataset for Perceptual Video Enhancement31
A Video quality assessment dataset for Perceptual Video Enhancement (VDPVE), which has 1211 videos with different enhancements, is constructed and the performance of several state-of-the-art video quality assessment methods on the test set of the VDPVE is verified.
- A No-Reference Deep Learning Quality Assessment Method for Super-Resolution Images Based on Frequency Maps31
This paper proposes a no-reference deep-learning image quality assessment method based on frequency maps that outperforms all compared IQA models on the selected three super-resolution quality assessment (SRQA) databases.
- 31
- Q-Boost: On Visual Quality Assessment Ability of Low-Level Multi-Modality Foundation Models30
Q-Boost is introduced, a novel strategy designed to enhance low-level MLLMs in image quality assessment (IQA) and video quality assessment (VQA) tasks, which is structured around two pivotal components: Triadic-Tone Integration and Multi-Prompt Ensemble.
- EEP-3DQA: Efficient and Effective Projection-Based 3D Model Quality Assessment30
This paper develops a no-reference (NR) Efficient and Effective Projection-based 3D Model Quality Assessment (EEP-3DQA) method and achieves the best performance than the existing state-of-the-art NR-3dQA methods and even outperforms most full-reference 3DQ a methods on the point cloud and mesh quality assessment databases while consuming less inference time than the compared 3D QA methods.
- 30
- 29
- 29
- Image Quality Assessment: From Human to Machine Preference28
The subjective preferences of machines are defined, including downstream tasks, test models, and evaluation metrics, and the Machine Preference Database is established, which contains 2.25M fine-grained annotations and 30k reference/distorted image pair instances.
- 28
- Q-Refine: A Perceptual Quality Refiner for AI-Generated Image28
Experimental data shows that for mainstream T2I models, Q-Refine can perform effective optimization to AIGIs of different qualities, thus expanding the application of the T2I generation models.
- DDH-QA: A Dynamic Digital Humans Quality Assessment Database28
A large-scale dynamic digital human quality assessment (DDH-QA) database with diverse motion content as well as multiple distortions to comprehensively study the perceptual quality of DDHs is constructed.
- Learning a Deep Agent to Predict Head Movement in 360-Degree Images28
This article proposes a model to predict the trajectory of head movement and stipulates that the model imitates the behaviors of human demonstrators, to ensure the accurate simulation of visual behaviors during the watching of panoramas.
- 28
- LMM4Edit: Benchmarking and Evaluating Multimodal Image Editing with LMMs27
This work introduces EBench-18K, the first large-scale image Editing Benchmark including 18K edited images with fine-grained human preference annotations for evaluating TIE, and proposes LMM4Edit, a LMM-based metric for evaluating image Editing models from perceptual quality, editing alignment, attribute preservation, and task-specific QA accuracy in an all-in-one manner.
- 27
- Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Model27
The Unify Generated Video Quality Assessment (UGVQ) model is proposed, designed to accurately evaluate the multi-dimensional quality of AIGC videos, and established a benchmark for evaluating existing quality assessment metrics on the LGVQ dataset.
- Enhancing blind video quality assessment with rich quality-aware features27
This paper proposes Rich Quality-aware features enabled Video Quality Assessment (RQ-VQA), a simple yet effective method to enhance BVQA by leveraging rich quality-aware features extracted from off-the-shelf BIQA and BVQA models.
- 27
- A brief survey on adaptive video streaming quality assessment27
It is found that existing video streaming QoE assessment models still have limited performance, which makes it difficult to be applied in practical communication systems, and based on the success of deep learned feature representations for traditional video quality prediction, the off-the-shelf deep convolutional neural network (DCNN) is applied.
- 27
- Ntire 2025 Challenge on Short-Form Ugc Video Quality Assessment and Enhancement: Methods and Results26
This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement, and introduces a new short-form UGC dataset tailored for single-image super-resolution, i.e., the KwaiSR dataset.
- 25
- 25
- 24
- 24
- 23
- AGHI-QA: A Subjective-Aligned Dataset and Metric for AI-Generated Human Images22
AGHI-QA is introduced, a large-scale benchmark specifically designed for quality assessment of AGHIs and AGHI-Assessor is proposed, a novel quality metric that integrates the large multimodal model (LMM) with domain-specific human features for precise quality prediction and identification of visible and distorted body parts in AGHIs.
- 22
- 22
- Fine localization and distortion resistant detection of multi-class barcode in complex environments22
A region-based end-to-end network to finely localize and classify 1D barcode and Quick Response (QR) code in complex environments is proposed and it is demonstrated that the method can resist some distortions by simulating barcode images of different image qualities.
- Assessment of Visually Induced Motion Sickness in Immersive Videos22
It is found that the velocity (frequency) of VOs, the time the authors immersed and the scenes’ contents will all influence the level of VIMS, and the QoE of immersive videos with real life content will be influenced correspondingly.
- 22
- EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessment21
This work introduces EEmo-Bench, a novel benchmark dedicated to the analysis of the evoked emotions in images across diverse content categories and adopts an emotion ranking strategy and employs the Valence-Arousal-Dominance as emotional attributes for emotional assessment.
- 21
- 21
- 21
- Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric20
An objective evaluation metric, named AI-Generated Human activity Video Quality metric (GHVQ), is developed, to automatically analyze the quality of human activity AGVs, and outperforms existing quality metrics on the Human-AGVQA dataset by a large margin.
- Subjective and Objective Quality-of-Experience Assessment for 3D Talking Heads20
The 3D Talking Heads Quality Assessment (THQA-3D) dataset is introduced, comprising 1,000 sets of distorted and 50 original TH mesh sequences (MSs) to facilitate quality assessment in 3D TH transmission and a multimodal Quality-of-Experience (QoE) method incorporating a Large Quality Model (LQM).
- Deep Portrait Quality Assessment. A NTIRE 2024 Challenge Survey20
The NTIRE 2024 Portrait Quality Assessment Challenge is reviewed, highlighting the proposed solutions and results, and providing a gauge for the current state-of-the-art in Portrait Quality Assessment.
- A Multiple Attributes Image Quality Database for Smartphone Camera Photo Quality Assessment20
Experimental results demonstrate that the current objective models are not suitable for SCPs, and quality metrics having high correlation with human visual perception are highly needed.
- 3DGCQA: A Quality Assessment Database for 3D AI-Generated Contents19
This paper introduces a novel 3DGC quality assessment dataset, 3DGCQA, built using 7 representative Text-to-3D generation methods, and reveals the presence of 6 common distortion categories in the generated 3DGCs.
- A No-Reference Quality Assessment Method for Digital Human Head19
A novel no-reference (NR) method based on Transformer is developed to deal with DHQA in a multi-task manner and shows that the proposed method well correlates with the subjective ratings and outperforms the state-of-the-art quality assessment methods.
- 19
- 19
- HazeCLIP: Towards Language Guided Real-World Image Dehazing18
HazeCLIP is introduced, a language-guided adaptation framework designed to enhance the real-world performance of pre-trained dehazing networks, Inspired by the Contrastive Language-Image Pre-training (CLIP) model’s ability to distinguish between hazy and clean images, and leverage it to evaluate dehazing results.
- 18
- 18
- Towards versatile multimedia quality assessment for visual communications17
This work introduces a versatile multimedia visual quality assessment framework, X-QA, which unifies quality assessment of images, videos, and 3D models within a single large multi-modal model (LMM).
- 17
- 17
- 17
- Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment17
This work introduces a new image quality assessment (IQA) task paradigm, **grounding-IQA**, which integrates multimodal referring and grounding with IQA to realize more fine-grained quality perception, thereby extending existing IQA.
- 17
- 17
- No-reference screen content video quality assessment17
This model uses a multi-scale approach to extract several groups of features, including gradient features, relative standard deviation features, compression features, frequency domain features and inter-frame features, and outperforms the existing full- and no-reference quality evaluation metrics.
- 17
- Quality Assessment of Free-Viewpoint Videos by Quantifying the Elastic Changes of Multi-Scale Motion Trajectories17
An elastic metric and multi-scale trajectory based video quality metric (EM-VQM) is proposed in this paper and outperforms the state-of-the-art metrics designed for free-viewpoint videos significantly and achieves a gain of 12.86% and 16.75% in terms of median Pearson linear correlation coefficient values on the two datasets compared to the best one, respectively.
- 17
- LMME3DHF: Benchmarking and Evaluating Multimodal 3D Human Face Generation with LMMs16
Experimental results show that LMME3DHF achieves state-of-the-art performance, surpassing existing methods in both accurately predicting quality scores for AI-generated 3D human faces and effectively identifying distortion-aware salient regions and distortion types, while maintaining strong alignment with human perceptual judgments.
- Dual-Branch Network for Portrait Image Quality Assessment16
A dual-branch network for portrait image quality assessment (PIQA) is introduced, which can effectively address how the salient person and the background of a portrait image influence its visual quality.
- Geometry-Aware Video Quality Assessment for Dynamic Digital Human16
This paper proposes a novel no-reference (NR) geometry-aware video quality assessment method for DDH-QA challenge, which achieves state-of-the-art performance on the DDH/QA database.
- 16
- 16
- HarmonyIQA: Pioneering Benchmark and Model for Image Harmonization Quality Assessment15
The first Image Quality Assessment Database for image Harmony evaluation (HarmonyIQAD) is introduced, which consists of 1,350 harmonized images generated by 9 different IHAs, and the corresponding human visual preference scores, and a Harmony Image Quality Assessment (HarmonyIQA), to predict human visual preference for harmonized images.
- LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation15
Love is proposed, a LMM-based metric for AIGV Evaluation from multiple dimensions including perceptual preference, text-video correspondence, and task-specific accuracy in terms of both instance level and model level, which achieves state-of-the-art performance on the AIGVE-60K dataset.
- AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment15
This work introduces AGAVQA-3k, the first large-scale AGAV quality assessment dataset, and proposes AGAV-Rater, a LMM-based model that can score AGAVs, as well as audio and music generated from text, across multiple dimensions, and selects the best AGAV generated by VTA methods to present to the user.
- Audio-Visual Saliency for Omnidirectional Videos15
This paper establishes the largest audio-visual saliency dataset for omnidirectional videos (AVS-ODV), which comprises the omniddirectional videos, audios, and corresponding captured eye-tracking data for three video sound modalities including mute, mono, and ambisonics, and compares the performance of several state-of-the-art saliency prediction models on the dataset.
- 15
- 15
- 15
- PuzzleBench: A Fully Dynamic Evaluation Framework for Large Multimodal Models on Puzzle Solving14
A fully dynamic multimodal evaluation framework, named Open-ended Visual Puzzle Generation (OVPG), which aims to generate fresh, diverse, and verifiable evaluation data automatically in puzzle-solving tasks, and constructs PuzzleBench, a dynamic and scalable benchmark comprising 11,840 VQA samples.
- DFBench: Benchmarking Deepfake Image Detection Capability of Large Multimodal Models14
This work proposes MoA-DF, Mixture of Agents for DeepFake detection, leveraging a combined probability strategy from multiple LMMs, which achieves state-of-the-art performance, further proving the effectiveness of leveraging LMMs for deepfake detection.
- BAND-2k: Banding Artifact Noticeable Database for Banding Detection and Quality Assessment14
An effective no-reference (NR) banding evaluator is developed for banding detection and quality assessment by leveraging frequency characteristics of banding artifacts, and a dual convolutional neural network is employed to concurrently learn the feature representation from the high-frequency and low-frequency maps.
- A Novel Lightweight Audio-visual Saliency Model for Videos14
This article is the first trial to utilize audio cues for an efficient deep-learning model for the video saliency estimation and validate the performance of the LAVS model in terms of effectiveness and complexity.
- 14
- 14
- 14
- ESIQA: Perceptual Quality Assessment of Vision-Pro-based Egocentric Spatial Images13
The Egocentric Spatial Images Quality Assessment Database (ESIQAD) is established, the first IQA database dedicated for egocentric spatial images as far as the authors know, and a novel mamba2-based multi-stage feature fusion model, termed ESIQAnet, which predicts the perceptual quality of egocentric spatial images under the three display modes.
- How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Model13
An in-depth analysis of how audio influences visual attention in ODVs is performed and an innovative omnidirectional audio-visual saliency prediction network (OmniAVS) is proposed, which is built based on the U-Net architecture, and hierarchically fuses audio and visual features from the multimodal aligned embedding space.
- AIS 2024 Challenge on Video Quality Assessment of User-Generated Content: Methods and Results13
This paper reviews the AIS 2024 Video Quality Assessment (VQA) Challenge, focused on User-Generated Content (UGC), to gather deep learning-based methods capable of estimating the perceptual quality of UGC videos.
- Masked Autoencoders as Image Processors13
This paper presents an efficient Transformer model considering both channel attention and shifted-window-based self-attention termed CSformer, and develops an effective MAE architecture for image processing (MAEIP) tasks.
- Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and Model12
This is the first work that studies the problem of text-guided 3D generation quality assessment, and an effective T23DAQA model is devised to evaluate the quality of AI generated 3D asset, which is more consistent with human perception.
- UNQA: Unified No-Reference Quality Assessment for Audio, Image, Video, and Audio-Visual Content12
The Unified No-reference Quality Assessment model (UNQA) is proposed, which tries to train a single QA model across different media modalities, and the multi-modality training strategy makes the QA model learn more general and robust quality-aware feature representation as evidenced by the superior performance of UNQA compared to state-of-the-art QA methods.
- 12
- 12
- 12
- 11
- 11
- Joint Gaze-Location and Gaze-Object Detection11
GTR is proposed, short for GTR, streamlining the gaze following detection pipeline by eliminating all additional components, leading to the first unified paradigm that unites GL-D and GO-D in a fully end-to-end manner.
- 11
- DevsNet: Deep Video Saliency Network using Short-term and Long-term Cues11
A novel deep learning framework of saliency detection for video sequences, namely Deep Video Saliency Network (DevsNet), which mainly consists of two components: 3D Convolutional Network (3D-ConvNet) and Bidirectional convolutional Long-Short Term Memory Network (B-ConVLSTM).
- 10
- Omni 2 : Unifying Omnidirectional Image Generation and Editing in an Omni Model10
Any2Omni, the first comprehensive ODI generation-editing dataset, is constructed and an Omni model for Omni-directional image generation and editing ( Omni 2) is proposed, with the capability of handling various ODI generation and editing tasks under diverse input conditions using one model.
- CompressedVQA-HDR: Generalized Full-reference and No-reference Quality Assessment Models for Compressed High Dynamic Range Videos10
This paper adopts the Swin Transformer and SigLip 2 as the backbone networks for the proposed full-reference and no-reference VQA models, respectively, and achieves state-of-the-art performance compared to existing FR and NR VQA models.
- VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results10
A novel benchmark comprising thousands of coarse-to-fine grained visual quality comparison tasks, spanning single images, pairs, and multi-image groups is introduced, which serves as a catalyst for future research on inter-pretable and human-aligned quality evaluation systems.
- MM-PCQA+: Advancing Multi-Modal Learning for Point Cloud Quality Assessment10
This work presents an advanced no-reference Multi-Modal Point Cloud Quality Assessment (MM-PCQA+) metric, which surpasses all state-of-the-art methods and significantly advances beyond previous no-reference PCQA methods.
- 10
- 10
- CMC-Bench: Towards a New Paradigm of Visual Signal Compression10
At ultra-low bitrates, this paper proves that the combination of some I2T and T2I models has surpassed the most advanced visual signal codecs; meanwhile, it highlights where LMMs can be further optimized toward the compression task.
- 10
- 10
- 10
- 10
- 10
- 10
- 10
- Multi-Dimensional Text-to-Face Image Quality Assessment Using LLM: Database and Method9
The Fine -grained Text-to-Face Image Quality Assessment (FineTFIQA) database is introduced, which is designed to evaluate the ability of T2I models to generate fine-grained face images and significantly outperforms existing methods on all evaluation dimensions.
- 9
- 9
- I2I-Bench: A Comprehensive Benchmark Suite for Image-to-Image Editing Models9
This work proposes I2I-Bench, a comprehensive benchmark for image-to-image editing models, which features diverse tasks, comprehensive evaluation dimensions, and rigorous alignment validation, justifying the consistency between benchmark evaluations and human preferences.
- 9
- How is Visual Attention Influenced by Text Guidance? Database and Model9
A text-guided saliency (TGSal) prediction model, which extracts and integrates both image features and text features to predict the image saliency under various text-description conditions, which significantly outperforms the state-of-the-art saliency models on both the SJTU-TIS database and the pure image saliency databases in terms of various evaluation metrics.
- MTCAM: A Novel Weakly-Supervised Audio-Visual Saliency Prediction Model With Multi-Modal Transformer9
- Quality-Guided Skin Tone Enhancement for Portrait Photography9
A quality-guided image enhancement paradigm is proposed that enables image enhancement models to learn the distribution of images with various quality ratings, which can be used to adjust images continuously according to different quality scores.
- Quantitative blood loss measurement methods for early detection of primary postpartum haemorrhage following vaginal birth: A scoping review9
This scoping review supports the replacement of the visual estimation of blood loss with quantitative assessment methods and suggests healthcare professionals need to acknowledge the low accuracy of visual estimation methods and implement quantitative methods to assess postpartum blood loss.
- Audio-Visual Quality Assessment for User Generated Content: Database and Method9
The first UGC AVQA database named the SJTU-UAV database is constructed, which includes 520 in-the-wild UGC audio and video (A/V) sequences, and the experimental results show that with the help of audio signals, the VQA models can evaluate the perceptual quality more accurately.
- Simple Baselines for Projection-based Full-reference and No-reference Point Cloud Quality Assessment9
This paper uses multi-projections obtained via a common cube-like projection process from the point clouds for both full- reference (FR) and no-reference (NR) PCQA tasks, and proposes simple baselines for projection-based point cloud quality assessment (PCQA) to tackle this challenge.
- 9
- 9
- 8
- 8
- VQualA 2025 Challenge on Face Image Quality Assessment: Methods and Results8
The VQualA 2025 Challenge on Face Image Quality Assessment (FIQA) as part of the ICCV 2025 Workshops created lightweight and efficient models for the prediction of Mean Opinion Scores (MOS) on face images with arbitrary resolutions and realistic degradations.
- Information Density Principle for MLLM Benchmarks8
A critical principle of Information Density is proposed, which examines how much insight a benchmark can provide for the development of MLLMs and shows that using the latest benchmarks in testing can provide more insight compared to previous ones, but there is still room for improvement in their information density.
- 8
- 8
- 8
- 8
- Calculation of ophthalmic diagnostic parameters on a single eye image based on deep neural network8
A two-phase algorithm to automatically measure these parameters instead of manual measurement to facilitate the diagnosis procedure of ptosis, eyelid retraction and other eye pathologies is designed and found that it can improve the measurements accuracy of eyelid, conjunctiva, cornea, sclera, and internal and external canthus, and promote efficiency and efficacy of relative clinical researches.
- Restoring Skeletal Marker Points for Severe Maxillary and Mandibular Jaw Defects Using a Linear Regression Approach8
This study sought to repair the personalized 3-dimensional shape of the jaw, particularly when the jaw is severely damaged to show that 2-dimensional regression has the best effect.
- 7
- Engagement Prediction of Short Videos with Large Multimodal Models7
This work empirically investigate the potential of large multimodal models (LMMs) for video engagement prediction by ensembling two representative LMMs: VideoLLaMA2, which integrates audio, visual, and language modalities, and Qwen2.5-VL, which models only visual and language modalities.
- Optimizing Projection-Based Point Cloud Quality Assessment with Human Preferred Viewpoints Selection7
- Boosting power line inspection in bad weather: Removing weather noise with channel-spatial attention-based UNet7
This paper constructs a power line components detection (PLCD) dataset, which includes 1943 power line images captured by UAVs and corresponding annotated bounding boxes, and proposes a new image restoration model termed CSUNet for better remove the noise and restore images.
- 7
- 7
- GazeGAN: A Generative Adversarial Saliency Model based on Invariance Analysis of Human Gaze During Scene Free Viewing.7
A novel saliency model based on generative adversarial network (dubbed GazeGAN) is introduced, which combines classic skip connections with a novel center-surround connection in order to leverage multi level features, and a histogram loss based on Alternative Chi Square Distance (ACS HistLoss) is proposed to refine the saliency map in terms of luminance distribution.
- 7
- 7
- RGC-VQA: An Exploration Database for Robotic-Generated Video Quality Assessment6
The concept of Robotic-Generated Content (RGC) is innovatively proposed to term these videos generated from egocentric perspective of robots to establish the first Robotic-Generated Content Database (RGCD), which contains a total of 2,100 videos drawn from three robot categories and sourced from diverse platforms.
- GOBench: Benchmarking Geometric Optics Generation and Understanding of MLLMs6
GOBench is introduced, the first benchmark to systematically evaluate MLLMs' ability across two tasks: Generating Optically Authentic Imagery and Understanding Underlying Optical Phenomena, revealing MLLMs' generation flaws that violate optical principles.
- 6
- ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos6
The first Egocentric Spatial Video Quality Assessment Database (ESVQAD) is introduced, and a novel multi-dimensional binocular feature fusion model, termed ESVQAnet, is proposed, which integrates binocular spatial, motion, and semantic features to predict the overall perceptual quality.
- Towards Effective User Attribution for Latent Diffusion Models via Watermark-Informed Blending6
This work introduces a novel framework Towards Effective user Attribution for latent diffusion models via Watermark-Informed Blending (TEAWIB), which incorporates a unique ready-to-use configuration approach that allows seamless integration of user-specific watermarks into generative models.
- Deep Decomposition and Bilinear Pooling Network for Blind Night-Time Image Quality Evaluation6
A novel deep decomposition and bilinear pooling network (DDB-Net) to better address the issue of night-time images (NTIs) which usually suffers from complicated authentic distortions such as reduced visibility, low contrast, additive noises, and color distortions.
- Subjective Quality Assessment for Images Generated by Computer Graphics6
A large-scale subjective CG-IQA database is established and several popular no-reference image quality assessment methods are tested, showing that the handcrafted-based methods achieve low correlation with subjective judgment and deep learning- based methods obtain relatively better performance.
- 6
- 6
- 6
- 6
- 5
- LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)5
This paper reports on the LoViF 2026 PhyScore challenge, a competition on holistic quality assessment of world-model-generated videos across both 2D and 4D generation settings, and provides method-level insights from submitted solutions.
- Quality Assessment and Distortion-Aware Saliency Prediction for AI-Generated Omnidirectional Images5
This work first studies the quality assessment and distortion-aware saliency prediction problems for AIGODIs, and presents a corresponding optimization process that utilizes the predicted visual experience scores and distortion regions to further enhance the visual quality of an AI-generated omnidirectional image.
- 5
- 5
- ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation5
An all-in-one model based on a Multimodal Large Language Model (MLLM) that leverages contrastive LoRA fine-tuning and task-specific decoders to achieve unified image manipulation detection, localization, and explanation is proposed.
- BMPCQA: Bioinspired Metaverse Point Cloud Quality Assessment Based on Large Multimodal Models5
A bioinspired metaverse point cloud quality assessment (BMPCQA) metric, which simulates the human visual evaluation process to perform the point cloud quality assessment (PCQA) task, paves the way for perceptually aligned and scalable point cloud quality assessment in next‐generation virtual environments.
- 5
- 5
- FS-BAND: A Frequency-Sensitive Banding Detector5
Experimental results show that the proposed FS-BAND method outperforms state-of-the-art image quality assessment (IQA) approaches with higher accuracy in banding classification task.
- 5
- Structured Computational Modeling of Human Visual System for No-reference Image Quality Assessment5
A novel perceptual no-reference IQA algorithm based on structural computational modeling of HVS is proposed, which is highly competitive with or outperforms the state-of-the-art NR IQA measures.
- 5
- Terahertz Security Image Quality Assessment by No-reference Model Observers5
The statistical results demonstrated the superiority of Fish_bb over the other testing IQA approaches for assessing the THz image quality with PLCC (SROCC) values of 0.8925, and the linear regression analysis and Bland-Altman plot further verified that the Fish__bb could substitute for the subjective IQA.
- 5
- 5
- 5
- EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment4
EEmoDB, the largest image-evoked emotion understanding dataset to date, is introduced and EEmo-Logic, an all-in-one multimodal large language model developed via instruction fine-tuning and task-customized group relative preference optimization (GRPO) with novel reward design is proposed.
- 4
- Q-Bench-Portrait: Benchmarking Multimodal Large Language Models on Portrait Image Quality Perception4
Q-Bench-Portrait is introduced, the first holistic benchmark specifically designed for portrait image quality perception, comprising 2,765 image-question-answer triplets and revealing that although current models demonstrate some competence in portrait image perception, their performance remains limited and imprecise, with a clear gap relative to human judgments.
- Multi-Dimensional Quality Assessment for AI-Generated Human-Centric Videos: Dataset and Model4
This work extends the previous dataset HVEval with pairwise preference annotations and proposes MoE-Rater, a Mixture-of-Experts (MoE)-inspired and multimodal large language model (MLLM)-based all-in-one method that supports multi-dimensional quality rating, multi-dimensional pairwise comparison, and category-specific question answering within a single model.
- Scaling-up Perceptual Video Quality Assessment4
This work proposes OmniVQA, a framework designed to efficiently build high-quality, machine-dominated synthetic multi-modal instruction databases (MIDBs) for VQA, and proposes the OmniVQA-FG (fine-grain)-Benchmark to evaluate the fine-grained performance of models.
- 4
- Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads4
This paper presents the largest AGTH quality assessment dataset THQA-10K to date, which selects 12 prominent T2I models and 14 advanced talkers to generate AGTHs for 14 prompts, and proposes an objective quality assessment method based on the first frame, Y-T slice and tonelip consistency.
- TIT-Score: Evaluating Long-Prompt Based Text-to-Image Alignment via Text-to-Image-to-Text Consistency4
A novel zero-shot metric based on text-to-image-to-text consistency, termed TIT, is introduced for evaluating long-prompt-generated images and achieves superior alignment with human judgment compared to CLIP-score, LMM-score, etc., with TIT-Score-LLM attaining a 7.31% absolute improvement in pairwise accuracy over the strongest baseline.
- Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes4
A comprehensive mesh saliency dataset is established, which is the first to systematically capture the differences in saliency distribution under both textured and non-textured visual conditions, and mesh Mamba is introduced, a unified saliency prediction model based on a state space model (SSM), designed to adapt across various mesh types.
- 4
- Compression-Realized Deep Structural Network for Video Quality Enhancement4
The Compression-Realized Deep Structural Network (CRDS) is proposed, introducing three inductive biases aligned with the three primary processes in the classic compression codec, merging the strengths of classical encoder architecture with deep network capabilities.
- 4
- 4
- 4
- 4
- Improving Accuracy of Jaw Reconstruction Based on Gender Differences4
The aim of the present study was to redetermine the position of the key points (skeletal marker points) in the damaged female and male jaws to improve the accuracy of jaw reconstruction.
- Leverage eye-movement data for saliency modeling: Invariance Analysis and a Robust New Model4
A novel saliency model based on generative adversarial network (dubbed GazeGAN) is introduced, which combines classic skip connections with a novel center-surround connection in order to leverage multi level features, and a histogram loss based on Alternative Chi Square Distance (ACS HistLoss) is proposed to refine the saliency map in terms of luminance distribution.
- A Saliency Dataset of Head and Eye Movements for Augmented Reality.4
To bridge the gap between the real-world scene and the scene augmented by virtual information, the ARVR saliency dataset is constructed with 100 diverse videos evaluated by 20 people and annotations of object recognition and tracking as augmented contents are blended into the omnidirectional videos.
- QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding3
QualiRAG is a training-free framework that systematically leverages the latent perceptual knowledge of large multimodal models (LMMs) for visual quality perception that achieves substantial improvements over open-source general-purpose LMMs and VQA-finetuned LMMs on visual quality understanding tasks, and delivers competitive performance on visual quality comparison tasks.
- 3
- 3
- Evaluating image editing with LLMs: A comprehensive benchmark and intermediate-layer probing approach3
Experimental results demonstrate that widely used automatic evaluation metrics show limited correlation with human judgments on editing tasks, while EditProbe achieves substantially stronger alignment with human perception.
- 3
- Towards Explainable Partial-AIGC Image Quality Assessment3
This work constructs the first large-scale PAI dataset towards explainable partial-AIGC image quality assessment (EPAIQA), the EPAIQA-15K, and proposes a three-stage model training paradigm that progressively trains the LMM for editing region grounding, quantitative quality scoring, and quality explanation.
- Efficient Face Image Quality Assessment via Self-Training and Knowledge Distillation3
This paper aims to develop a computationally efficient FIQA method that can be easily deployed in real-world applications and achieves first place in the ICCV 2025 VQualA FIQA Challenge.
- 3
- 3
- 3
- Explore the Hallucination on Low-level Perception for MLLMs3
This paper presents QL-Bench, a benchmark settings to simulate human responses to low-level vision, and investigates self-awareness in low-level visual perception through visual question answering related to low-level attributes such as clarity and lighting.
- EvalTalker: Learning to Evaluate Real-Portrait-Driven Multi-Subject Talking Humans3
This work constructs THQA-MT, the first large-scale Multi-Talker-generated Talking Human Quality Assessment dataset, and introduces EvalTalker, a novel TH quality assessment framework that possesses the ability to perceive global quality, human characteristics, and identity consistency, while integrating Qwen-Sync to perceive multimodal synchrony.
- 3
- Mitigating Low-Level Visual Hallucinations Requires Self-Awareness: Database, Model, and Training Strategy3
The HLPU instruction database is introduced, the first instruction database specifically focused on hallucinations in low-level vision tasks are introduced, and the Self-Awareness Failure Elimination (SAFEQA) model is proposed, which utilizes image features, salient region features and quality features to improve the perception and comprehension abilities of the model in low-level vision tasks.
- Textured Mesh Saliency: Bridging Geometry and Texture for Human Perception in 3D Graphics3
This work presents a new dataset for textured mesh saliency, created through an innovative eye-tracking experiment in a six degrees of freedom (6-DOF) VR environment, that addresses the limitations of previous studies by providing comprehensive eye-tracking data from multiple viewpoints, thereby advancing the understanding of human visual behavior and supporting more accurate and effective 3D content creation.
- 3
- 3
- 3
- 3
- 3
- Parameterized Image Quality Score Distribution Prediction3
This paper proposes a framework and an algorithm to predict the alphastable model based IQSD, where quality features are extracted from each image based on structural information and statistical information, and support vector regressors are trained to predictthe alpha stable model parameters.
- 3
- 3
- 3
- 3
- Subjective and Objective Quality-of-Experience Evaluation Study for Live Video Streaming2
An end-to-end QoE evaluation model is proposed, Tao-QoE, which implicitly encodes statistical Quality of Service (QoS) features, integrates multi-scale semantic features and optical flow-based motion features to predict a retrospective QoE score.
- 2
- 2
- 2
- 2
- Towards a New Paradigm of Visual Signal Compression2
CMC- Bench, a benchmark of the cooperative performance of Image-to- Text (I2T) and Text-to-Image (T2I) models for image compression, proves that the combination of some I2T and T2I models has surpassed the most advanced visual signal codecs; meanwhile, it highlights where LMMs can be further optimized toward the compression task.
- 2
- Neural mechanisms of visual quality perception and adaptability in the visual pathway2
Using functional magnetic resonance imaging (fMRI), this work decodes quality from fMRI and proposes a neural network feature fusion strategy, boosting ResNet’s VQA performance by 14.29% on the BID dataset (586 instances).
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- A Reading Assistant System for Blind People Based on Hand Gesture Recognition2
A reading assistant system for blind people based on hand gesture recognition is proposed and can realize perfect reading assistant function.
- 2
- Influence of Spatial Resolution on State-of-the-Art Saliency Models2
This work systematically investigate and analyze problems concerning spatial resolution in the research of saliency modeling and can provide a guide to the use of classic models in images of different resolutions and they are helpful to computational complexity optimization.
- 2
- 2
- ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning1
ReasonEdit is developed, which is trained using reward signals derived from RE-Reward and the Group Relative Policy Optimization (GRPO) algorithm to learn an interpretable evaluation model, and achieves superior alignment with human preferences and exhibits strong generalization across public benchmarks.
- 1
- 1
- Fine-Grained Human Pose Editing Assessment via Layer-Selective MLLMs1
HPE-Bench is introduced, a specialized benchmark comprising 1,700 standardized samples from 17 state-of-the-art editing models, offering both authenticity labels and multi-dimensional quality scores, and a unified framework based on layer-selective multimodal large language models (MLLMs) is proposed, effectively bridging the gap between forensic detection and quality assessment.
- Subjective and Objective QoE Assessment for Real-Time Streaming Interactive Digital Human1
Based on extensive subjective evaluations, SAV-PF is proposed, an audio–visual quality assessment method built on the human foundation model Sapiens and informed by cognitive principles such as the primacy effect and forgetting curve that achieves superior performance over existing objective QoE assessment approaches, providing a more accurate prediction of user experience.
- DocIQ: A Benchmark Dataset and Feature Fusion Network for Document Image Quality Assessment1
DocIQ is proposed, which combines layout-aware downsampling with a multi-level feature fusion module to effectively capture both structural and semantic quality cues and outperforms state-of-the-art general-purpose IQA methods on both DIQA-5000 and the OCR-based SmartDoc-QA benchmark.
- Decoupling Perception and Calibration: Label-Efficient Image Quality Assessment Framework1
This work proposes LEAF, a Label-Efficient Image Quality Assessment Framework that distills perceptual quality priors from an MLLM teacher into a lightweight student regressor, enabling MOS calibration with minimal human supervision, making lightweight IQA practical under limited annotation budgets.
- 1
- 1
- Exploring Image Quality Assessment from a New Perspective: Pupil Size1
This research can not only provide a theoretical basis for the objective IQA method and promote the development of more effective objective IQA methods, but also provide a new subjective IQA method for collecting the authentic subjective impression of image quality.
- 1
- Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method1
LiveBeauty is presented, the first large-scale live-specific FAP dataset, in a more challenging application scenario, i.e., live streaming, and a multi-modal FAP method is proposed to measure the facial attractiveness in live streaming.
- Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation1
This work presents Adapter Shield, the first universal and authentication-integrated solution aimed at defending personal images from misuse in zero-shot generation scenarios, and designs a multi-target adversarial perturbation method that actively shifts the original embeddings toward designated encrypted patterns.
- 1
- 1
- 1
- 1
- 1
- Hidden Barcode in Sub-Images with Invisible Locating Marker1
Human perceptual characteristics are considered and an optimal hiding region recommendation algorithm that comprehensively incorporates Just Noticeable Difference and visual saliency factors into consideration is introduced that comprehensively incorporates Just Noticeable Difference and visual saliency factors into consideration.
- fMRI Exploration of Visual Quality Assessment1
This study pioneers the intersection of neuroscience and image quality research, providing empirical evidence through fMRI linking image quality to neural processing and contributes novel insights into the human visual system's response to diverse image qualities, thereby paving the way for advancements in objective image quality assessment algorithms.
- Audio-visual aligned saliency model for omnidirectional video with implicit neural representation learning1
A novel audio-visual aligned saliency (AVAS) model is proposed that can simultaneously tackle two issues as mentioned above in an effective end-to-end training manner and consistently outperforms other competitors by a large margin.
- Perceptual Quality Assessment for Video Frame Interpolation1
A no-reference perceptual quality assessment method that applies a triplet network architecture to extract the deep perceptual features of the interpolated frame as well as the original pair of frames incorporating the original pair of VFI inputs is proposed.
- 1
- 1
- 1
- The New Frontier of Quality Evaluation for Visual Sensors: A Survey of Large Multimodal Model-Based Methods–
A unified perspective on visual quality assessment for sensor-captured visual data across image, video, and 3D modalities is presented, highlighting how multimodal fusion and language-conditioned reasoning transform quality assessment from scalar prediction to perceptual intelligence.
- –
- Preference-guided debiasing for no-reference enhancement image quality assessment–
A preference-guided debiasing framework for no-reference enhancement image quality assessment (EIQA) that effectively mitigates algorithm-induced representation bias and achieves superior robustness and cross-algorithm generalization compared with existing approaches.
- –
- ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing–
The resulting benchmark sets a new standard for industrial defect analysis research and requires assigning each detected defect an industry-standard severity level, including Acceptable, Marginal NG, NG, and Gross NG.
- DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation–
DyCoRM is proposed, a dynamic, criterion-aware reward model that grounds task-relevant criteria and performs criterion-aware preference comparison and establishes the first reward modeling framework for dynamic and fine-grained evaluation and practical application in T2I generation.
- DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models–
DynT2I-Eval is proposed, a fully automated dynamic evaluation framework for T2I models that constructs a structured visual semantic space from long-form descriptions, decomposing prompts into controllable dimensions (e.g., subject, logical constraint, environment, and composition).
- –
- –
- –
- –
- –
- –
- –
- –
- –
- GeoR-Bench: Evaluating Geoscience Visual Reasoning–
GeoR-Bench is presented, a Benchmark for evaluating geoscience visual visual reasoning through reasoning informed visual editing tasks, and its findings indicate that current models generate superficially plausible results but fail to capture underlying earth science processes.
- –
- –
- SalDiff-DTM: A Novel Dual-Temporal Modulated Diffusion Model for Omnidirectional Images Scanpath Prediction–
A saliency-guided diffusion module that formulates the prediction problem as a conditional generative process, iteratively yielding accurate and perceptually plausible scanpaths is proposed, paving the way for future advancements in eye-tracking technologies and cognitive modeling.
- –
- –
- ITIScore: An Image-to-Text-to-Image Rating Framework for the Image Captioning Ability of MLLMs–
A new large-scale image captioning benchmark is presented, termed, ICBench, which consists of both short and long captions generated by 10 advanced MLLMs on 2K images, resulting in 40K captions in total, and an automated evaluation metric is proposed, based on an image-to-text-to-image framework, which measures caption quality through reconstruction consistency.
- –
- –
- –
- Generative Human-Object Interaction Detection via Differentiable Cognitive Steering of Multi-modal LLMs–
A novel Generative Reasoning And Steerable Perception framework that reformulates HOI detection from the closed-set classification task to the open-vocabulary generation problem, and introduces a hybrid guidance strategy that coupling the language modeling loss and auxiliary classification loss, enabling discriminative grounding without sacrificing generative flexibility.
- –
- –
- –
- –
- Elevating Mesh Saliency in VR: Introducing a Novel Prediction Network and Dataset–
This work establishes a novel mesh saliency dataset, facilitated by a more comprehensive gathering pipeline of eye-tracking from subjects observing mesh models at arbitrary viewpoints in a virtual reality space with six degrees of freedom, and proposes a mesh saliency prediction model that accurately infers visual attention density maps for complex and irregular mesh surfaces.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- A Lightweight Segmentation Network Based on Weak Supervision for COVID-19 Detection–
The convex-hull based segmentation (CHS) loss function is proposed in this paper, which enables the model to obtain an approximate fully supervised performance on point labels and combines the advantages of lightweight and weak supervision, resulting in more accurate COVID-19 lesion segmentation results while having only a 10% performance difference with the fully supervised approach.
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.