Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks95 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.
- Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives463
The Disentangled Objective Video Quality Evaluator (DOVER) is proposed, the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective, and the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective.
- TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment423
This work proposes a top-down approach that uses high-level semantics to guide the IQA network to focus on semantically important local distortion regions, named as TOPIQ, and designs a heuristic coarse-to-fine network that leverages multi-scale features and progressively propagates multi-level semantic information to low-level representations in a top-down manner.
- Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision309
Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment, confirms that MLLMs possess preliminary low-level visual skills.
- STAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition292
Experimental re-sults show that the STAR-Net can achieve a performance comparable to state-of-the-art methods for scene texts with little distortions, and outperform these methods for scene texts with considerable distortions.
- 239
- Blind Face Restoration via Deep Multi-scale Component Dictionaries230
A deep face dictionary network (termed as DFDNet) to guide the restoration process of degraded observations and can achieve plausible performance in both quantitative and qualitative evaluation, and can generate realistic and promising results on real degraded images without requiring an identity-belonging reference.
- Q-Instruct: Improving Low-Level Visual Abilities for Multi-Modality Foundation Models218
The first dataset consisting of human natural language feedback on low-level vision, and a GPT-participated transformation to convert these feedbacks into a rich set of 200K instruction-response pairs, termed Q-Instruct are collected.
- Progressive Semantic-Aware Style Transformation for Blind Face Restoration206
A new progressive semantic-aware style transformation framework, named PSFR-GAN, for face restoration, which makes full use of the semantic and pixel space information from different scales of input pairs and pretrain a face parsing network which can generate decent parsing maps from real-world LQ face images.
- Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors202
This work proposes Feature Matching SR (FeMaSR), which restores realistic HR images in a much more compact feature space by matching distorted LR image features to their distortion-free HR counterparts in the authors' pretrained HR priors, and decoding the matched features to obtain realisticHR images.
- Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition183
This work introduces a novel hierarchical attention mechanism (HAM) which consists of a recurrent RoIWarp layer and a character-level attention layer which can handle different types of distortion that are hard, if not impossible, to be modelled by a single global transformation.
- Towards Open-ended Visual Quality Comparison121
This work demonstrates that Co-Instruct not only achieves in average 30% higher accuracy than state-of-the-art open-source LMMs, but also outperforms GPT-4V (its teacher), on both existing related benchmarks and the proposed MICBench.
- Neighbourhood Representative Sampling for Efficient End-to-End Video Quality Assessment99
This work proposes a unified scheme, spatial-temporal grid mini-cube sampling (St-GMS), and the resultant samples are named fragments, a network architecture tailored specifically for fragments that achieves up to 1612× efficiency than the existing state-of-the-art VQA benchmarks.
- DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment86
The proposed Temporal Distortion-Content Transformers for Video Quality Assessment (DisCoVQA) reaches state-of-the-art performance on several VQA benchmarks without any extra pre-training datasets and up to 10% better generalization ability than existing methods.
- 84
- A Novel Gait Pattern Recognition Method Based on LSTM-CNN for Lower Limb Exoskeleton81
A novel gait pattern recognition method based on Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) for lower limb exoskeleton can identify the switching gait patterns in time, which shows that it has good real-time performance.
- Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach80
The MaxVQA is proposed, a language-prompted VQA approach that modifies vision-language foundation model CLIP to better capture important quality issues as observed in the authors' analyses.
- HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset78
This work introduces a coarse-to-fine deep learning framework for HDR video reconstruction, which outperforms previous state-of-the-art methods and conducts more sophisticated alignment and temporal fusion in the feature space of the coarse HDR video to produce better reconstruction.
- 75
- 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.
- 52
- S$^3$-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint48
This paper addresses the "dual problem" of multi-view scene reconstruction in which single-view images captured under different point lights are utilized to learn a neural scene representation, which is robust to depth discontinuities.
- MIMO Is All You Need：A Strong Multi-in-Multi-Out Baseline for Video Prediction44
Surprisingly, empirical studies reveal that a simple MIMO model can outperform the state-of-the-art work with a large margin much more than expected, especially in dealing with long-term error accumulation.
- Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment41
Experiments show that the perceptual representation in the HVS is an effective way of predicting subjective temporal quality, and thus TPQI can, for the first time, achieve comparable performance to the spatial quality metric and be even more effective in assessing videos with large temporal variations.
- Semi-supervised Learning for Face Sketch Synthesis in the Wild41
A semi-supervised deep learning architecture is proposed which extends face sketch synthesis to handle face photos in the wild by exploiting additional facePhotos in training by performing patch matching in feature space between the input photo and photos in a small reference set of photo-sketch pairs.
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.