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
- Liang WangSuggested from co-authorship
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works112 from public data
- Single Image Super-Resolution via a Holistic Attention Network857
A new holistic attention network (HAN) is proposed, which consists of a layer attention module (LAM) and a channel-spatial attention Module (CSAM) to model the holistic interdependencies among layers, channels, and positions.
- 549
- Deblurring by Realistic Blurring494
This paper proposes a new method which combines two GAN models, i.e., a learning-to-Blur GAN (BGAN) and learning- to-DeBlurGAN (DBGAN), in order to learn a better model for image deblurring by primarily learning how to blur images.
- 487
- Deep Image Deblurring: A Survey415
This paper presents a comprehensive and timely survey of recently published deep-learning based image deblurring approaches, aiming to serve the community as a useful literature review.
- Deep Dense Multi-Scale Network for Snow Removal Using Semantic and Depth Priors370
This paper proposes a Deep Dense Multi-Scale Network for snow removal by exploiting semantic and geometric priors, and designs a DDMSNet to learn semantic-aware and geometry-aware representation via a self-attention mechanism to produce the final clean images.
- MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing291
A new Transformer variant, named Multi-branch Transformer expanded by Taylor formula (MB-TaylorFormer), which can em-bed coarse to fine features more flexibly at the patch embedding stage and capture long-distance pixel interactions with limited computational cost.
- MB-TaylorFormer V2: Improved Multi-Branch Linear Transformer Expanded by Taylor Formula for Image Restoration277
The proposed model, named the second version of Taylor formula expansion-based Transformer (for short MB-TaylorFormer V2) has the capability to concurrently process coarse-to-fine features, capture long-distance pixel interactions with limited computational cost, and improve the approximation of the Taylor expansion remainder.
- GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions240
The GridFormer framework achieves state-of-the-art results on five diverse image restoration tasks in adverse weather conditions, including image deraining, dehazing, deraining & dehazing, desnowing, and multi-weather restoration.
- Enhanced Spatio-Temporal Interaction Learning for Video Deraining: Faster and Better220
A new end-to-end video deraining framework, dubbed Enhanced Spatio-Temporal Interaction Network (ESTINet), which considerably boosts current state-of-the-art video derained quality and speed and takes the advantage of deep residual networks and convolutional long short-term memory.
- MC-Blur: A Comprehensive Benchmark for Image Deblurring188
This paper constructs a new large-scale multi-cause image deblurring dataset (MC-Blur), including real-world and synthesized blurry images with different blur factors, and conducts extensive benchmarking studies to compare SOTA methods in different scenarios, analyze their efficiency, and investigate the buildataset’s capacity.
- Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification186
A Noise Resistible Mutual-Training (NRMT) method, which maintains two networks during training to perform collaborative clustering and mutual instance selection, which outperforms the state-of-the-art UDA methods for person re-ID.
- All-in-One Weather-Degraded Image Restoration Via Adaptive Degradation-Aware Self-Prompting Model160
This work develops an adaptive degradation-aware self-prompting model (ADSM) for all-in-one weather-degraded image restoration that employs the contrastive language-image pre-training model (CLIP) to facilitate the training of the proposed latent prompt generators (LPGs).
- 144
- 134
- Kinship Verification with Deep Convolutional Neural Networks111
This paper proposes to extract high-level features for kinship verification based on deep convolutional neural networks based on deep convolutional neural networks, and considers the importance of facial key-points, to extract key-points-based features for kinship veri-cation.
- 110
- ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring92
Quantitative and qualitative experiments show that the proposed implicit method to learn spatial correspondence among blurry frames in the feature space performs favorably on both datasets against previous state-of-the-art methods, confirming the benefit of modeling all-range spatial correspondence for video deblurring.
- 80
- Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior78
A Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information is presented, and a Semantic-Aware Deraining Module (SADM) is developed which solves both tasks of semantic segmentation and deraining of scenes.
- 74
- 70
- Deep Two-View Structure-from-Motion Revisited69
This work proposes to revisit the problem of deep two-view SfM by leveraging the well-posedness of the classic pipeline by developing a scale-invariant depth estimation network that leverages epipolar geometry to reduce the search space, refine the dense correspondences, and estimate relative depth maps.
- Visual style prompt learning using diffusion models for blind face restoration63
A visual style prompt learning framework that utilizes diffusion probabilistic models to explicitly generate visual prompts within the latent space of pre-trained generative models to guide the restoration process and introduces a style-modulated aggregation transformation layer.
- T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing59
This paper proposes a dehazing network named T-Net, which consists of a backbone network based on the U-Net architecture and a dual attention module, and proposes a recursive strategy to take advantage of the dependence of deep features across stages via a recursion strategy.
- Vicinity Vision Transformer58
Vicinity Attention, which is a type of linear attention that integrates 2D locality that achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous approaches, is proposed.
- 56
- Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding55
A Paired Rain Removal Network (PRRNet) is presented, which exploits both stereo images and semantic information, and a Semantic-Aware Deraining Module (SADM) which solves both tasks of semantic segmentation and deraining of scenes, and a Semantic-Fusion Network (SFNet) and a View-Fusion Network (VFNet) which fuse semantic information and multi-view information respectively.
- 46
- From heavy rain removal to detail restoration: A faster and better network45
A simple dual-stage progressive enhancement network, denoted as DPENet, aiming to achieve effective deraining while preserving the structural accuracy of rain-free images and employs a comprehensive loss function that accentuates both the marginal and regional accuracy of rain-free images.
- 42
- Pyramid Architecture Search for Real-Time Image Deblurring42
A novel deblurring method, dubbed PyNAS (pyramid neural architecture search network), towards automatically designing hyper-parameters including the scales, patches, and standard cell operators, and uses a path-level binarization mechanism for multi-scale cell searching to save the memory consumption.
- 41
- 39
- Towards Real-World Blind Face Restoration with Generative Diffusion Prior35
This work proposes BFRffusion which is thoughtfully designed to effectively extract features from low-quality face images and could restore realistic and faithful facial details with the generative prior of the pretrained Stable Diffusion and builds a privacy-preserving face dataset called PFHQ with balanced attributes like race, gender, and age.
- MaterialMVP: Illumination-Invariant Material Generation via Multi-View PBR Diffusion34
MaterialMVP, a novel end-to-end model for generating PBR textures from 3D meshes and image prompts, addressing key challenges in multi-view material synthesis is presented, outperforming existing methods in both consistency and quality for scalable 3D asset creation.
- 34
- Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition30
This work proposes Set-of-Vision-Text Prompting (SoVTP), a novel framework that enhances zero-shot emotion recognition by integrating spatial annotations, physiological signals, and contextual cues into a unified prompting strategy that preserves holistic scene information while enabling fine-grained analysis of facial muscle movements and interpersonal dynamics.
- 30
- 29
- 28
- EDFace-Celeb-1 M: Benchmarking Face Hallucination With a Million-Scale Dataset25
A public Ethnically Diverse Face dataset is built, EDFace-Celeb-1 M, and a benchmark task for face hallucination is designed, demonstrating the performance and limitations of state-of-the-art algorithms.
- Every Moment Matters: Detail-Aware Networks to Bring a Blurry Image Alive24
A detail-aware network with three consecutive stages to improve the reconstruction quality by addressing specific aspects in the recovery process and produces sharp image sequences with rich details and subtle motion, outperforming the state-of-the-art methods.
- 22
- Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency22
A human parsing based texture transfer model via cross-view consistency learning to generate the texture of 3D human body from a single image to reduce the appearance variation of human image and preserve the spatial distribution of semantic parts.
- Cousin Network Guided Sketch Recognition via Latent Attribute Warehouse22
This paper proposes to transfer the knowledge of a network learned from natural images to a sketch network - a new deep net architecture which is term as cousin network, which guides a sketch-recognition network to extract more relevant features that are close to those of natural images, via adversarial training.
- Blind Face Restoration for Under-Display Camera via Dictionary Guided Transformer19
This work proposes a two-stage network UDC Degradation Model Network named UDC-DMNet to synthesize UDC images by modeling the processes of UDC imaging, and introduces the facial component dictionary and the characteristics of the UDC image in the restoration makes DGFormer capable of addressing blind face restoration in UDC scenarios.
- 19
- PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal16
A novel prompt-guided reflection removal (PromptRR) framework that uses frequency information as new visual prompts for better reflection performance, decouples the reflection removal process into the prompt generation and subsequent prompt-guided restoration.
- Deep Face Restoration: A Survey16
This paper comprehensively surveys recent advances in deep learning techniques for face restoration and presents a comprehensive review of existing FR methods, including prior based methods and deep learning-based methods.
- 15
- 15
- Fast Ultra High-Definition Video Deblurring via Multi-scale Separable Network15
A novel deep model for fast and accurate UHD video deblurring (UHDVD) is proposed by a depth-wise separable-patch architecture, which operates with a multi-scale integration scheme to achieve a large receptive field without adding the number of generic convolutional layers and kernels.
- 15
- EchoSR: Efficient context harnessing for lightweight image super-resolution14
EchoSR is proposed, an efficient context-harnessing framework for lightweight image super-resolution, which unifies multi-scale receptive field modeling and hierarchical context fusion and further promotes seamless cross-scale integration via a cross-scale overlapping fusion mechanism.
- Prompting Future Driven Diffusion Model for Hand Motion Prediction13
A prompt-based Future Driven Diffusion Model (PromptFDDM) for predicting hand motion with guidance and prompts is proposed, which achieves state-of-the-art performance in both first-and third-person perspectives.
- Blind Face Video Restoration with Temporal Consistent Generative Prior and Degradation-Aware Prompt13
StableBFVR features a novel mixed-degradation-aware prompt module, capable of encoding specific degradation information to dynamically steer the restoration process, and outperforms state-of-the-art methods.
- Homography Guided Temporal Fusion for Road Line and Marking Segmentation13
A Homography Guided Fusion module to exploit temporally-adjacent video frames for complementary cues facilitating the correct classification of the partially occluded road lines or markings is proposed and shown to lead to a light-weight network with significantly improved performances in speed and accuracy.
- 12
- 12
- Multiprior Learning Via Neural Architecture Search for Blind Face Restoration12
A face restoration searching network to adaptively search the suitable feature extraction architecture within the authors' specified search space, which can directly contribute to the restoration quality and the multiple facial prior searching network (MFPSNet) with a multiprior learning scheme.
- Deep robust image deblurring via blur distilling and information comparison in latent space12
A latent contrastive model, Blur Distilling and Information Reconstruction Networks (BDIRNet), to learn image prior and improve the robustness of deep deblurring and achieve improved and robust results compared to recent state-of-the-art methods.
- 10
- Dual Teacher Knowledge Distillation With Domain Alignment for Face Anti-Spoofing9
A domain adversarial attack method by adding perturbations to the input images, which makes them indistinguishable across domains and enables domain alignment, which develops a dual teacher knowledge distillation with domain alignment framework (DTDA) for face anti-spoofing.
- Displacement-Invariant Cost Computation for Stereo Matching9
This work proposes a displacement-invariant cost computation module to compute the matching costs without needing a 4D feature volume, and proposes an entropy-based refinement strategy to refine the computed disparity map, which further improves the speed by avoiding the need to compute a second disparity map on the right image.
- 9
- 8
- 8
- 7
- Model Calibration in Dense Classification with Adaptive Label Perturbation7
Adaptive Stochastic Label Perturbation (ASLP) is proposed which learns a unique label perturbation level for each training image and improves model calibration degree by minimising the gap between the prediction accuracy and expected confidence of the target training label.
- DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution6
DAM-VSR is proposed, an appearance and motion disentanglement framework for VSR that achieves state-of-the-art performance on real-world data and AIGC data, demonstrating its powerful detail generation capabilities.
- AuslanWeb: A Scalable Web-Based Australian Sign Language Communication System for Deaf and Hearing Individuals6
AuslanWeb, a web-based system for bidirectional translation of both isolated and successive sign language, integrating linguistic structure with advanced AI capabilities, overcomes the limitations of dataset dependency and enhances the scalability of sign language translation systems.
- Generalised Co-Salient Object Detection6
A novel random sampling based Generalised CoSOD Training (GCT) strategy to distill the awareness of inter-image absence of co-salient objects into coSOD models by allowing the presence of "noisy images" which do not show the shared co-Salient object.
- 6
- UHDRes: Ultra-High-Definition Image Restoration via Dual-Domain Decoupled Spectral Modulation5
This paper proposes UHDRes, a novel lightweight dual-domain decoupled spectral modulation framework for UHD image restoration that explicitly models the amplitude spectrum via lightweight spectrum-domain modulation, while restoring phase implicitly through spatial-domain refinement.
- 5
- 5
- scSFCL:Deep clustering of scRNA-seq data with subspace feature confidence learning5
By validation on multiple scRNA-seq datasets, it is shown that the clustering performance of scSFCL is significantly improved compared with traditional methods, providing an effective solution for deep clustering of scRNA-seq data.
- 4
- Benchmarking Ultra-High-Definition Image Reflection Removal4
A transformer-based architecture named RRFormer for reflection removal is presented, demonstrating through experimental results that RRFormer achieves state-of-the-art performance on both the non-UHD dataset and the proposed UHDRR datasets.
- 4
- 4
- Dual Alignment-Enhanced Fashion Vision-Language Pre-Training3
Experimental results spanning four diverse downstream tasks, including cross-modal retrieval, text-guided image retrieval, category recognition, and subcategory recognition, substantiate the significant performance superiority of this model over prior state-of-the-art fashion VLP models.
- 3
- 3
- 3
- Deep Video Restoration for Under-Display Camera3
This work proposes a novel transformer-based baseline method that adaptively enhances degraded videos of UDC-VR and builds the first large-scale UDC video restoration dataset called PexelsUDC, which includes two subsets corresponding to different displays for UDC.
- 3
- 2
- 2
- 2
- 2
- Authentic Emotion Mapping: Benchmarking Facial Expressions in Real News2
This paper presents a novel benchmark for Emotion Recognition using facial landmarks extracted from realistic news videos, leveraging Graph Neural Networks to analyze the geometric and spatial relationships of facial landmarks and discusses the advancements and challenges in deep learning techniques for emotion recognition.
- 1
- 1
- Embodied heritage by integrating digital and physical visualization of eaves tiles to display cultural heritage kinship1
A 3D interactive visualization system is developed that facilitates cross-dynasty exploration of eave tiles, leveraging generative AI for motif restoration and prediction, and the transition from digital visualization to physical representation using thermochromic materials for digital light processing 3D printing is investigated.
- LLDif: Diffusion Models for Low-light Emotion Recognition1
Experimental evaluations on various LL-FER datasets have shown that LLDif achieves competitive performance, underscoring its potential to enhance FER applications in challenging lighting conditions.
- InterTracker: Discovering and Tracking General Objects Interacting with Hands in the Wild1
This paper proposes to leverage spatio-temporal information of hand-object interaction to track interactive objects under these challenging cases and demonstrates that the proposed method outperforms the state-of-the-art methods.
- Aircraft type recognition in 3D-view optical image with contour segmentation1
A fast contour template matching approach with a new matching evaluation criterion and an aircraft contour template database for aircraft contour template matching is proposed for aircraft type recognition in 3D-view images.
- 1
- Benchmarking Deep Deblurring Algorithms: A Large-Scale Multi-Cause Dataset and A New Baseline Model.1
- –
- –
- –
- –
- –
- Deep image restoration in adverse weather: A survey–
A comprehensive survey is presented that jointly organizes single-task and AiO restoration models from the perspectives of network architectures and learning paradigms and summarizes benchmark results of representative methods on public datasets to analyze their performance and generalization ability.
- DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation–
This work designs a degradation-aware structure auto-encoder with degradation-informed routing regularization to predict clean structural priors from degraded inputs, and introduces a structure-guided wavelet interaction mechanism to bridge frequency-domain features and spatial semantics.
- ResiHMR: Residual-Limb Aware Single-Image 3D Human Mesh Recovery for Individuals with Limb Loss–
This work presents ResiHMR, a residual-limb aware framework for single-image 3D human modeling that explicitly reconstructs residual-limb surfaces and performs topology-adaptive optimization for individuals with limb loss.
- –
- Adversarial Purification and Fine-tuning for Robust UDC Image Restoration–
This study delves into the enhancement of Under-Display Camera (UDC) image restoration models, focusing on their robustness against adversarial attacks, and introduces a defense framework integrating adversarial purification with subsequent fine-tuning processes.
- –
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 2026-10-15. 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.