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
- Ming–Hsuan YangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works189 from public data
- 1,955
- Single Image Dehazing via Multi-scale Convolutional Neural Networks1,809
A multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps by combining a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale network which refines results locally.
- Multi-Scale Boosted Dehazing Network With Dense Feature Fusion1,100
This paper designs a dense feature fusion module that can simultaneously remedy the missing spatial information from high-resolution features and exploit the non-adjacent features and develops a simple yet effective boosted decoder to progressively restore the haze-free image.
- Gated Fusion Network for Single Image Dehazing953
An efficient algorithm to directly restore a clear image from a hazy input using an end-to-end trainable neural network that consists of an encoder and a decoder is proposed.
- 820
- 489
- 445
- 409
- Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges387
A multi-scale deep neural network for single image dehazing by learning the mapping between hazy images and their transmission maps by combining a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale network which refines dehazed results locally.
- 312
- 297
- Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution279
This work proposes a spatially-adaptive feature modulation (SAFM) mechanism for efficient SR design that is 3× smaller than state-of-the-art efficient SR methods, e.g., IMDN, and yields comparable performance with much less memory usage.
- 260
- 247
- 243
- Spatio-Temporal Filter Adaptive Network for Video Deblurring237
The proposed Spatio-Temporal Filter Adaptive Network (STFAN) takes both blurry and restored images of the previous frame as well as blurry image of the current frame as input, and dynamically generates the spatially adaptive filters for the alignment and deblurring.
- Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration226
- Learning Dual Convolutional Neural Networks for Low-Level Vision221
The proposed DualCNN consists of two parallel branches, which respectively recovers the structures and details in an end-to-end manner, and can generate the target signals according to the formation model for each particular application.
- Unpaired Deep Image Deraining Using Dual Contrastive Learning205
An effective unpaired SID adversarial framework which explores mutual properties of the unpaired exemplars by a dual contrastive learning manner in a deep feature space, named as DCD-GAN is developed.
- Learning Fully Convolutional Networks for Iterative Non-blind Deconvolution200
The proposed fully convolutional network is able to learn an adaptive image prior, which keeps both local and global information, and performs favorably against state-of-the-art algorithms in terms of quality and speed.
- Physics-Based Generative Adversarial Models for Image Restoration and Beyond188
An algorithm to directly solve numerous image restoration problems (e.g., image deblurring, image dehazing, and image deraining) by generative models with adversarial learning within the GAN framework.
- Physics-Based Feature Dehazing Networks184
An effective feature dehazing unit (FDU), which is applied to the deep feature space to explore useful features for image dehazed based on the physics model, and can effectively dehaze images with favorable performance against state-of-the-art methods.
- Cascaded Deep Video Deblurring Using Temporal Sharpness Prior182
A temporal sharpness prior to constrain the deep CNN model to help the latent frame restoration and it is shown that exploring the domain knowledge of video deblurring is able to make the deepCNN model more compact and efficient.
- Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network169
Experimental results show that many low-level vision tasks can be effectively learned and carried out in real-time by the proposed algorithm and is significantly smaller and faster in comparison with a deep CNN based image filter.
- 167
- Deblurring Face Images with Exemplars165
A maximum a posteriori (MAP) deblurring algorithm based on an exemplar dataset, without using the coarse-to-fine strategy or ad-hoc edge selections is proposed, which addresses the problems ofdeblurring face images by exploiting facial structures.
- Learning Event-Driven Video Deblurring and Interpolation163
An effective event-driven video deblurring and interpolation algorithm based on deep convolutional neural networks (CNNs) that achieves superior performance against state-of-the-art methods on both synthetic and real datasets.
- Learning a Discriminative Prior for Blind Image Deblurring160
This work forms the image prior as a binary classifier which can be achieved by a deep convolutional neural network (CNN) and is able to distinguish whether an input image is clear or not.
- LSTM Pose Machines148
It is shown that if the weight sharing scheme is imposed to the multi-stage CNN, it could be re-written as a Recurrent Neural Network (RNN), which decouples the relationship among multiple network stages and results in significantly faster speed in invoking the network for videos.
- 135
- Kernel estimation from salient structure for robust motion deblurring135
This paper developed a novel method for computing image structures based on the TV model, such that the structures undermining the kernel estimation will be removed and proposed a novel kernel estimation method, which is capable of removing noise and preserving the continuity in the kernel.
- 133
- Blind Image Deblurring via Deep Discriminative Priors118
This work forms the image prior as a binary classifier using a deep convolutional neural network to handle image dehazing and develops an efficient numerical approach based on the half-quadratic splitting method and gradient descent algorithm to optimize the proposed model.
- 117
- 115
- 112
- PromptRestorer: A Prompting Image Restoration Method with Degradation Perception111
A prompting degradation perception modulator is proposed, which adequately considers the characters of the self-attention mechanism and pixel-wise modulation, to better perceive the degradation priors from global and local perspectives.
- DAVANet: Stereo Deblurring With View Aggregation108
This work proposes a novel stereo image deblurring network with Depth Awareness and View Aggregation, named DAVANet, which outperforms state-of-the-art methods in terms of accuracy, speed, and model size.
- 106
- Video Deblurring via Semantic Segmentation and Pixel-Wise Non-linear Kernel105
This paper analyzes the relationship between motion blur trajectory and optical flow, and presents a novel pixel-wise non-linear kernel model to account for motion blur, which describes complex motion blur more effectively.
- 104
- Correlation Matching Transformation Transformers for UHD Image Restoration102
Experimental results show that the UHDformer reduces about ninety-seven percent model sizes compared with most state-of-the-art methods while significantly improving performance under different training sets on 3 UHD image restoration tasks, including low-light image enhancement, image dehazing, and image deblurring.
- Deep Blind Video Super-resolution98
An effective blind video SR algorithm based on deep convolutional neural networks (CNNs) and an effective sharp feature exploration method which first extracts sharp features from restored intermediate latent frames and then uses a transformation operation based on the extracted sharp features and warped features from LR inputs to generate better features for HR video restoration.
- Deep Non-Blind Deconvolution via Generalized Low-Rank Approximation96
The authors' analysis shows that the estimated decomposed matrices contain the most essential information of the input kernel, which ensures the proposed network to handle various blurs in a unified framework and generate high-quality deblurring results.
- Memory-Augmented Deep Unfolding Network for Guided Image Super-resolution93
A maximum a posteriori (MAP) estimation model for GISR with two types of priors on the HR target image, i.e., local implicit prior and global implicit prior is proposed, and a novel alternating optimization algorithm is designed to solve this model.
- Efficient Visual State Space Model for Image Deblurring92
This paper proposes a simple yet effective visual state space model (EVSSM) for image deblurring, leveraging the benefits of state space models (SSMs) for visual data, and proposes an efficient discriminative frequency domain-based feedforward network (EDFFN), which can effectively estimate useful frequency information for latent clear image restoration.
- Hybrid CNN-Transformer Feature Fusion for Single Image Deraining92
A lightweight Hybrid CNN-Transformer Feature Fusion Network (dubbed as HCT-FFN) is proposed in a stage-by-stage progressive manner, which can harmonize these two architectures to help image restoration by leveraging their individual learning strengths.
- The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report91
This paper provides a comprehensive review of the NTIRE 2024 challenge, focusing on efficient single-image super-resolution (ESR) solutions and their outcomes, and gauge the state-of-the-art in efficient single-image super-resolution.
- 89
- Learning to Deblur Images with Exemplars84
This paper proposes a deblurring algorithm based on an exemplar dataset without using coarse-to-fine strategies or heuristic edge selections, and develops a convolutional neural network to restore sharp edges from blurry images fordeblurring.
- 77
- Towards Unified Deep Image Deraining: A Survey and a New Benchmark72
An online platform is built to provide the off-the-shelf toolkit, involving the large-scale performance evaluation of existing image deraining methods, and a new high-quality benchmark named HQ-RAIN is constructed to conduct extensive evaluations.
- Deep Recurrent Neural Network with Multi-Scale Bi-directional Propagation for Video Deblurring72
A simple and effective deep Recurrent Neural Network with Multi-scale Bi-directional Propagation (RNN-MBP) to effectively propagate and gather the information from unaligned neighboring frames for better video deblurring.
- 70
- 68
- 68
- 66
- 62
- Joint Face Hallucination and Deblurring via Structure Generation and Detail Enhancement60
This paper proposes a facial component guided deep Convolutional Neural Network to restore a coarse face image, which is denoted as the base image where the facial component is automatically generated from the input face image.
- 59
- 59
- Dual Convolutional Neural Networks for Low-Level Vision59
Experimental results show that the DualCNN can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods that have been specially designed for each individual task.
- 57
- FoundIR: Unleashing Million-Scale Training Data to Advance Foundation Models for Image Restoration54
A diffusion-based generalist model is utilized to remove degradations by learning the degradation-agnostic common representations from diverse inputs, where an incremental learning strategy is adopted to better guide model training.
- 52
- 50
- Learning Data Terms for Non-blind Deblurring46
This work proposes a simple and effective discriminative framework to learn data terms that can adaptively handle blurred images in the presence of severe noise and outliers and shows that the shrinkage functions learned at the intermediate stages can effectively suppress noise and preserve image structures.
- 45
- Deep Blind Image Inpainting42
This work presents an efficient blind image inpainting algorithm to directly restore a clear image from a corrupted input and can predict the missing information in the corrupted regions, thus facilitating the clear image restoration.
- 41
- BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-Based Video Colorization40
A BiSTNet to explore colors of exemplars and utilize them to help video colorization by a bidirectional temporal feature fusion with the guidance of semantic image prior is presented.
- 40
- 39
- Deep Richardson–Lucy Deconvolution for Low-Light Image Deblurring37
A data-driven approach to model the saturated pixels by a learned latent map is developed and performs favorably against state-of-the-art algorithms both quantitatively and qualitatively on synthetic and real-world images.
- 37
- 36
- 35
- 34
- 34
- 33
- 31
- 31
- 30
- Blur kernel estimation via salient edges and low rank prior for blind image deblurring30
It is found that the blur process changes the similarity of neighboring image patches and based on the intriguing observation, it is shown how to effectively apply the low rank prior to blind image deblurring and a new algorithm is presented that combines low rankPrior and salient edge selection.
- 29
- Self-Supervised Deep Blind Video Super-Resolution29
A simple and effective method to generate auxiliary paired data from original LR videos according to the image formation of video SR, so that the networks can be better constrained by the generated paired data for both blur kernel estimation and latent HR video restoration.
- 29
- 29
- 28
- 26
- Learning to Deblur Face Images via Sketch Synthesis26
An effective face deblurring algorithm based on deep convolutional neural networks (CNNs) that is able to deblur face images with favorable performance against state-of-the-art methods.
- Multi-task Image Restoration Guided By Robust DINO Features24
It is observed that the features of DINOv2 can effectively model semantic information and are independent of degradation factors, and a multi-task image restoration approach leveraging robust features extracted from DINOv2 to solve multi-task image restoration simultaneously is proposed.
- Real-World Image Super-Resolution by Exclusionary Dual-Learning24
This paper proposes a method, Real-World image Super-Resolution by Exclusionary Dual-Learning (RWSR-EDL) to address the feature diversity in perceptual- and L1- based cooperative learning and develops a noise-guidance data collection strategy to addressed the training time consumption in multiple datasets optimization.
- 24
- 23
- 22
- DnSwin: Toward real-world denoising via a continuous Wavelet Sliding Transformer22
This article proposes a continuous Wavelet Sliding-Transformer that builds frequency correspondences under real-world scenes, called DnSwin, which extracts the bottom features from noisy input images by using a convolutional neural network (CNN) encoder and reconstructs them into denoised images using a CNN decoder.
- DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution21
This paper proposes the DORNet, a novel framework designed to adaptively address unknown degradation in real-world scenes through implicit degradation representations, and introduces a degradation-oriented feature transformation module that selectively propagates RGB content into the depth data based on the learned degradation priors.
- Ultra-High-Definition Image Restoration: New Benchmarks and a Dual Interaction Prior-Driven Solution19
This paper constructs UHD snow and rain benchmarks, named UHD-Snow and UHD-Rain, and proposes an effective UHD image restoration solution by considering gradient and normal priors in model design, thanks to these priors’ spatial and detail contributions.
- 19
- 18
- UltraVSR: Achieving Ultra-Realistic Video Super-Resolution with Efficient One-Step Diffusion Space16
A novel framework that enables ultra-realistic and temporally-coherent VSR through an efficient one-step diffusion space and introduces a Temporally Asynchronous Inference (TAI) strategy to capture long-range temporal dependencies under limited memory constraints is proposed.
- Deep Unpaired Blind Image Super-Resolution Using Self-supervised Learning and Exemplar Distillation16
An exemplar distillation module is developed that is able to explore useful information from exemplar HR images to constrain the deep models learned from the self-supervised learning module for the final HR image restoration.
- 16
- 15
- Multi-Stage Degradation Homogenization for Super-Resolution of Face Images With Extreme Degradations15
- Image Formation Model Guided Deep Image Super-Resolution15
This work presents a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution and shows that the proposed algorithm performs favorably against state-of-the-art methods.
- DeblurDiff: Real-World Image Deblurring with Generative Diffusion Models14
The proposed Latent Kernel Prediction Network (LKPN) outperforms state-of-the-art image deblurring methods on both benchmark and real-world images and iterative refinement enhances the accuracy and robustness of the deblurring process.
- 13
- Blind Image Deblurring Using Elastic-Net Based Rank Prior13
The proposed prior is based on an elastic-net regularization of singular values and it favors clear images over blurred images and it is able to facilitate the kernel estimation in the conventional maximum a posterior framework.
- 13
- L0-Regularized Object Representation for Visual Tracking13
A robust visual tracking method by L0-regularized prior in a particle filter framework that achieves state-of-the-art results both in accuracy and speed is proposed.
- Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement12
A super-resolution-guided reconstruction approach, which is guided by super-resolving low-resolution features to facilitate final UHD image restoration and enhancement and enhances the quality of restored images.
- 12
- Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration12
A coarse-to-fine diffusion Transformer (C2F-DFT) for image restoration that significantly outperforms diffusion-based restoration method IR-SDE and achieves competitive performance compared with Transformer-based state-of-the-art methods on $3$ tasks, including image deraining, image deblurring, and real image denoising.
- FoundIR-v2: Optimizing Pre-Training Data Mixtures for Image Restoration Foundation Model10
This work proposes a high-capacity diffusion-based image restoration foundation model, FoundIR-v2, which adopts a data equilibrium scheduling paradigm to dynamically optimize the proportions of mixed training datasets from different tasks, and introduces an effective Mixture-of-Experts (MoE)-driven scheduler into generative pre-training.
- 10
- 9
- Intelligence Science and Big Data Engineering. Visual Data Engineering9
An IA-DSM scheme is proposed for solving a doubly stochastic matrix (DSM) featured combinatorial tasks such as travelling salesman problem, and also a Subtree driven reasoning scheme is suggested for improving production rule based reasoning.
- 8
- 8
- Scene Prior Filtering for Depth Super-Resolution7
A Scene Prior Filtering network, SPFNet, which utilizes the priors’ surface normal and semantic map from large-scale models and designs a One-to-one Prior Embedding that continuously embeds every single modal prior into depth using Mutual Guided Filtering, further alleviating texture interference while enhancing edge representations.
- 7
- Efficient Concertormer for Image Deblurring and Beyond7
Concertormer is introduced, featuring Concerto Self-Attention (CSA) for image deblurring, featuring Concerto Self-Attention (CSA) for image deblurring, and the gated-dconv MLP merges the two-staged Transformer design into a single stage.
- 7
- Robust dense correspondence using deep convolutional features7
Deep features extracted from pretrained convolutional neural networks are explored to help the estimation of image matching so that dense pixel correspondence can be built and performed favorably against state-of-the-art methods.
- 7
- Non-uniform motion deblurring with Kernel grid regularization6
The theoretical framework of blur Kernels is analyzed, a robust Kernel estimation algorithm based on Earth mover’s distance (Wasserstein metric) is proposed, and a new Kernel refinement method based on a proposed Ink Dot Diffusion that uses 8 directions of Kernel mapping flow to improve blur Kernel estimation.
- 5
- 5
- 5
- 5
- Single image rain removal via densely connected contextual and semantic correlation net5
This work designs a deraining unit that employs dilation convolution and squeeze-and-excitation operations, respectively, to obtain more spatial contextual information and semantic correlation and interconnect the deraining units by dense connections that can maximize the information flow along features from different levels and make them be associated.
- Learning Deblurring Texture Prior From Unpaired Data with Diffusion Model4
TP-Diff provides a promising unsupervised deblurring solution and outperforms SOTA methods in widely-used benchmarks and implements a waveletbased adversarial loss to preserve high-frequency texture details.
- Deep self-supervised spatial-variant image deblurring4
This paper proposes a self-supervised learning-based image deblurring method that can deal with both uniform and spatial-variant blur distributions and achieves favorable performance against existing image deblurring methods.
- Harmonizing Light and Darkness: A Symphony of Prior-guided Data Synthesis and Adaptive Focus for Nighttime Flare Removal4
A plug-and-play Adaptive Focus Module (AFM) that can adaptively mask the clean background areas and assist models in focusing on the regions severely affected by flares is proposed.
- 4
- AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results3
This paper thoroughly evaluates the state-of-the-art advances in high-FPS single image motion deblurring, showcasing the significant progress in the field, while leveraging samples of the novel dataset, MIORe, that introduces challenging examples of movement patterns.
- VJT: A Video Transformer on Joint Tasks of Deblurring, Low-light Enhancement and Denoising3
This work builds a novel multi-tier transformer where each tier uses a different level of degraded video as a target to learn the features of video effectively and carefully design a new tier-to-tier feature fusion scheme to learn video features incrementally and accelerate the training process with a suitable adaptive weighting scheme.
- 3
- Debluring Low-Resolution Images3
A super-resolution guided method to help the restoration of reliable image structures which can be used for kernel estimation and shows that the SR results obtained as byproducts in the method are comparable compared to other blind SR methods.
- 2
- Collaborative Feedback Discriminative Propagation for Video Super-Resolution2
This work develops a discriminative alignment correction (DAC) method and proposes a collaborative feedback propagation (CFP) module based on feedback and gating mechanisms to explore spatial and temporal information of different timestep features from forward and backward propagation simultaneously.
- 2
- 2
- 2
- PatchScaler: An Efficient Patch-Independent Diffusion Model for Image Super-Resolution2
This work introduces a Patch-adaptive Group Sampling (PGS) strategy that groups feature patches by quantifying their reconstruction difficulty and establishes shortcut paths with different sampling configurations for each group to further optimize the patch-level reconstruction process of PGS.
- 2
- 2
- Technique Report of CVPR 2024 PBDL Challenges2
This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging.
- 2
- 2
- Intelligence Science and Big Data Engineering. Big Data and Machine Learning2
The location method based on Received Signal Strength Indication (RSSI) ranging has the advantages of low development cost and simple implementation mechanism, and is the mainstream indoor location method nowadays but there is a lack of systematic research on the characteristics of Access Point (AP) received signal strength.
- Blind Image Deblurring via Salient Structure Detection and Sparse Representation2
A new algorithm that combines salient image structure detection and sparse representation for blind image deblurring and a sparse representation based \(\ell _1\)-norm deconvolution model is proposed for suppressing noise robustly and solving for a high-quality latent image.
- Robust optical flow estimation based on brightness correction fields2
A brightness correction field combined with a gradient constancy constraint to reduce the sensibility to brightness changes between images to be estimated and is more effective and produces more accurate results for optical flow estimation.
- 1
- Cascaded Temporal Updating Network for Efficient Video Super-Resolution1
This work proposes a cascaded temporal updating network (CTUN) for efficient VSR, and develops an implicit cascaded alignment module to explore spatio-temporal correspondences from adjacent frames and a unidirectional propagation updating network to efficiently explore long-range temporal information, which is crucial for high-quality video reconstruction.
- How Powerful Potential of Attention on Image Restoration?1
This paper proposes Continuous Scaling Attention (CSAttn), a method that computes attention continuously in three stages without using FFN and applies it to several image restoration tasks and shows that it can outperform CNN-based and Transformer-based image restoration approaches.
- 1
- –
- MiM-DiT: MoE in MoE with Diffusion Transformers for All-in-One Image Restoration–
A unified image restoration framework that integrates a dual-level Mixture-of-Experts architecture with a pretrained diffusion model that enables the model to achieve coarse-grained adaptation across diverse degradation categories while performing fine-grained modulation for specific intra-class variations.
- –
- –
- –
- Cross-Scenario Deraining Adaptation With Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesize–
This framework functions as a versatile plug-and-play module capable of seamless integration into arbitrary deraining architectures, and yields remarkable PSNR gains of up to 32% to 59% in OOD domains while significantly accelerating training convergence.
- Wavelet-Based Adaptive Vision State Space Network for Image Harmonization–
A wavelet-based adaptive vision state space network to harmonize local regions by comprehensively exploiting long-range background context is proposed and a low-frequency harmonization block is introduced to aggregate global context and capture foreground–background interactions.
- –
- MFSR: Multi-Fractal Feature for Super-Resolution Reconstruction With Fine Details Recovery–
MFSR is a diffusion model-based super-resolution method that incorporates multi-fractal features of low-resolution images as texture priors to enhance fine detail recovery and confirms that incorporating multi-fractal features consistently improves SR3, SRDiff, and ResDiff.
- –
- Multi-Modal Object Re-Identification with Dual Semantic Guidance and Global-Local Mutual Modulation–
A robust multi-modal ReID framework with dual semantic guidance and global-local mutual modulation, which mainly consists of three key components, namely the Text-Semantic Injector (TSI), the Masked Global-Local Modulator (MGLM), and the Hierarchical MoE Fusion (HMF).
- Degradation-Aware Prompt Learning With Cross-Modal Compensation for Adverse Weather Removal–
A Degradation-Aware Cross-Modal Prompt Compensation Network that leverages cross-modal degradation cues from a pre-trained vision-language model to condition restoration features within a unified backbone, achieving robust and perceptually consistent restoration across diverse weather conditions.
- –
- –
- –
- –
- Spread Your Wings: A Radial Strip Transformer for Image Deblurring–
A Radial Strip Transformer (RST), which is a transformer-based architecture that restores the blur images in a polar coordinate system instead of a Cartesian one, and a radial strip attention solver (RSAS) as deep feature extraction, where the relationship of windows is organized by azimuth and radius.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.