Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks129 from public data
- 2,300
- Learning Deep CNN Denoiser Prior for Image Restoration2,156
Experimental results demonstrate that the learned set of denoisers can not only achieve promising Gaussian denoising results but also can be used as prior to deliver good performance for various low-level vision applications.
- 1,259
- Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision842
It is proved that WNNP is equivalent to a standard quadratic programming problem with linear constrains, which facilitates solving the original problem with off-the-shelf convex optimization solvers and presents an automatic weight setting method, which greatly facilitates the practical implementation of WNNM.
- Learning Convolutional Networks for Content-Weighted Image Compression421
The bit rate of the different parts of the image is adapted to local content, and the content-aware bit rate is allocated under the guidance of a content-weighted importance map so that the sum of the importance map can serve as a continuous alternative of discrete entropy estimation to control compression rate.
- 370
- 366
- Projective dictionary pair learning for pattern classification328
Compared with conventional DL methods, the proposed DPL method can not only greatly reduce the time complexity in the training and testing phases, but also lead to very competitive accuracies in a variety of visual classification tasks.
- You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network296
A novel method, called you only look yourself (YOLY), which could be one of the first unsupervised and untrained neural networks for image dehazing which bypasses the conventional training paradigm of deep models on hazy-clean pairs or a large scale dataset, thus avoids the labor-intensive data collection and the domain shift issue.
- Frequency Separation for Real-World Super-Resolution282
DSGAN is proposed to introduce natural image characteristics in bicubic downscaled images to improve the performance of the SR model and separate the low and high image frequencies and treat them differently during training.
- Video Super-Resolution with Recurrent Structure-Detail Network269
A novel recurrent video super-resolution method which is both effective and efficient in exploiting previous frames to super-resolve the current frame by dividing the input into structure and detail components which are fed to a recurrent unit composed of several proposed two-stream structure-detail blocks.
- 266
- 245
- Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression220
This paper analyzes two popular network compression techniques, i.e. filter pruning and low-rank decomposition, in a unified sense and proposes to compress the whole network jointly instead of in a layer-wise manner.
- 220
- 203
- Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training173
This paper proposes a novel domain-distance aware super-resolution (DASR) approach for unsupervised real-world image SR and results show that DASR consistently outperforms state-of-the-art un supervised SR approaches in generating SR outputs with more realistic and natural textures.
- 173
- Efficient Video Super-Resolution through Recurrent Latent Space Propagation173
An efficient recurrent latent space propagation algorithm for fast VSR that introduces high-dimensional latent states to propagate temporal information between frames in an implicit manner and outperform current state-of-the-art method DUF with over 70x speed-up.
- Flow-based Kernel Prior with Application to Blind Super-Resolution164
This paper proposes a normalizing flow-based kernel prior (FKP) that optimizes the kernel in the latent space rather than the network parameter space, which allows it to generate reasonable kernel initialization, traverse the learned kernel manifold and improve the optimization stability.
- PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report161
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones and proposes solutions that significantly improved baseline results defining the state-of-the-art for image enhancement on smartphones.
- Improving Deep Video Compression by Resolution-Adaptive Flow Coding149
A new framework called Resolution-adaptive Flow Coding (RaFC) is proposed to effectively compress the flow maps globally and locally, in which multi-resolution representations are used for both the input flow maps and the output motion features of the MV encoder.
- DHP: Differentiable Meta Pruning via HyperNetworks140
This paper introduces a differentiable pruning method via hypernetworks for automatic network pruning, and extensive experiments are conducted on various networks for image classification, single image super-resolution, and denoising.
- Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary136
A group of auxiliary Adaptive Token Dictionary to SR Transformer is introduced and an ATD-SR method is established to establish an adaptive refinement step that achieves the best performance on various single image super-resolution benchmarks.
- AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results123
The AIM 2019 challenge on real world super-resolution addresses the real world setting, where paired true high and low-resolution images are unavailable, and aims to advance the state-of-the-art and provide a standard benchmark for this newly emerging task.
- 123
- Revisiting Random Channel Pruning for Neural Network Compression119
The proposed approach provides a new way to compare different methods, namely how well they behave compared with random pruning, and it is shown that this simple strategy works quite well compared with other channel pruning methods.
- 118
- 111
- Exemplar Guided Face Image Super-Resolution Without Facial Landmarks110
A convolutional neural network (CNN)-based solution, namely GWAInet, which applies super-resolution by a factor 8x on face images guided by another unconstrained HR face image of the same person with possible differences in age, expression, pose or size is proposed.
- Learning Filter Basis for Convolutional Neural Network Compression108
This paper tries to reduce the number of parameters of CNNs by learning a basis of the filters in convolutional layers, and validate the proposed solution for multiple CNN architectures on image classification and image super-resolution benchmarks.
- 102
- Learning Content-Weighted Deep Image Compression95
An upper-triangular masked convolutional network (triuMCN) for large context modeling is proposed, where the channel-wise multi-valued quantization is deployed for the discretization of the encoder features, and an importance map subnet is introduced to generate the importance masks for spatially varying code pruning.
- VA-DepthNet: A Variational Approach to Single Image Depth Prediction89
It is shown that imposing first-order variational constraints in the scene space together with popular encoder-decoder-based network architecture design provides excellent results for the supervised SIDP task.
- NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results85
This paper meticulously evaluates the state-of-the-art advancements in enhancing low-light images, reflecting the significant progress and creativity in this field.
- 82
- Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report69
The target is to develop an end-to-end deep learning-based video super-resolution solutions that can achieve a realtime performance on mobile GPUs and can upscale videos to HD resolution at up to 80 FPS while demonstrating high fidelity results.
- 64
- A Brief Review of Image Denoising Algorithms and Beyond64
An overview of prior modeling approaches used in image denoising task is presented, and conventional sparse representation based Denoising algorithms, low-rank based denoizing algorithms and recently proposed deep neural networks based approaches are reviewed.
- AIM 2019 Challenge on Constrained Super-Resolution: Methods and Results63
This paper reviews the AIM 2019 challenge on constrained example-based single image super-resolution with focus on proposed solutions and results and gauges the state-of-the-art in single imagesuper-resolution.
- NTIRE 2021 Challenge on Perceptual Image Quality Assessment60
The NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021, achieved much better results than existing IQA methods, while the winning method can demonstrate state-of-the-art performance.
- Improved Implicit Neural Representation with Fourier Reparameterized Training58
A Fourier reparameterization method which learns coefficient matrix of fixed Fourier bases to compose the weights of MLP is proposed and theoretically prove that weight reparameterization could provide a chance to alleviate the spectral bias of MLP.
- Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention57
A novel feature-level masked processing frame-work: VSR with Masked Intra and inter-frame Attention (MIA-VSR), which improves the memory and computation efficiency over state-of-the-art methods, without trading off PSNR accuracy.
- NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results54
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results and gauges the state-of-the-art in single image super- resolution.
- Progressive Focused Transformer for Single Image Super-Resolution51
A novel and effective Progressive Focused Transformer (PFT) is proposed that links all isolated attention maps in the network through Progressive Focused Attention (PFA) to focus attention on the most important tokens and significantly reduces the computational cost of the overall network.
- Learned Image Compression with Dictionary-Based Entropy Model51
A novel entropy model named Dictionary-Based Cross Attention Entropy model is proposed, which introduces a learnable dictionary to summarize the typical structures occurring in the training dataset to enhance the entropy model.
- 49
- CARN: Convolutional Anchored Regression Network for Fast and Accurate Single Image Super-Resolution47
The convolutional anchored regression network (CARN) is proposed for fast and accurate single image super-resolution (SISR), Inspired by locally linear regression methods (A+ and ARN), and achieves the best speed and accuracy trade-off among the SR methods.
- 45
- Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model44
This work finds that different regions of the LR image can be viewed as corresponding to different timesteps in a diffusion process, and proposes to apply uncertainty estimate to guide region-specific noise level control, a technique known as Uncertainty- guided Noise Weighting.
- 43
- 39
- NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results35
The 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results establishes a new benchmark for stereo image SR.
- Causal Context Adjustment Loss for Learned Image Compression32
This paper makes the first attempt in investigating the way to explicitly adjust the causal context with the proposed Causal Context Adjustment loss (CCA-loss), and enables the neural network to spontaneously adjust important information into the early stage of the autoregressive entropy model.
- 32
- AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results32
This paper reviews the video extreme super-resolution challenge associated with the AIM 2020 workshop at ECCV 2020 and gauges the state-of-the-art for such a demanding task, where fidelity to the ground truth is measured by PSNR and SSIM.
- 32
- 32
- NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results29
This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.
- 29
- Measuring Perceptual Color Differences of Smartphone Photographs26
This article puts together so far the largest image dataset for perceptual CD assessment, and makes one of the first attempts to construct an end-to-end learnable CD formula based on a lightweight neural network, as a generalization of several previous metrics.
- Mfagan: A Compression Framework for Memory-Efficient On-Device Super-Resolution Gan25
A novel compression framework for reducing the memory access cost of the generator by utilizing a memory-efficient multi-scale feature aggregation net as the generator and introducing the PatchGAN discriminator for faster and more stable training.
- Single Image Depth Prediction Made Better: A Multivariate Gaussian Take25
Per-pixel depth covariance modeling leads to a computationally expensive continuous loss function, which the SIDP model obtained by optimizing the learned low-rank approximation of the overall covariance matrix shows state-of-the-art results.
- 24
- Weighted image fusion based on multi-scale top-hat transform: Algorithms and a comparison study24
The experimental results indicate that, the weighted image fusion algorithms based on multi-scale top-hat transform may be widely used in different applications, such as target detection, object recognition and security surveillance, for image fusion.
- 23
- NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results23
This paper summarizes the 3rd NTIRE challenge on stereo image super-resolution with a focus on new solutions and results and establishes a new benchmark for stereo image SR.
- 23
- 22
- Consistency Trajectory Matching for One-Step Generative Super-Resolution21
Consistency Trajectory Matching for Super-Resolution (CTMSR) is proposed, a distillation-free strategy that is able to generate photo-realistic SR results in one step and minimize the discrepancy between their respective PF-ODE trajectories from the LR image distribution by the meticulously designed Distribution Trajectory Matching (DTM) loss.
- The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures21
This paper investigates a design space that is usually overlooked, i.e. adjusting the channel configurations of predefined networks, and finds that this adjustment can be achieved by shrinking widened baseline networks and leads to superior performance.
- 20
- 20
- Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks19
A Mask Guided Acceleration (MGA) scheme to reduce the computational costs of existing SR networks while maintaining their SR capability and experiments demonstrate that the MGA scheme reduces the FLOPs of five popular SR networks by 10% ∼ 48% with comparable or even better SR performance.
- 18
- Joint Image Denoising and Disparity Estimation via Stereo Structure PCA and Noise-Tolerant Cost18
A new joint framework is proposed that iteratively optimizes these two different tasks in a multiscale fashion and achieves superior performance than the state-of-the-art image denoising and disparity estimation methods.
- Guiding a Diffusion Transformer with the Internal Dynamics of Itself16
A simple yet effective strategy Internal Guidance (IG), which introduces an auxiliary supervision on the intermediate layer during training process and extrapolates the intermediate and deep layer's outputs to obtain generative results during sampling process, yields significant improvements in both training efficiency and generation quality on various baselines.
- 16
- PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Model13
This paper introduces PerLDiff (Perspective-Layout Diffusion Models), a novel method for effective street view image generation that fully leverages perspective 3D geometric information and demonstrates superior controllability compared to alternative layout control methods.
- 12
- Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning12
UVIT, a novel unsupervised video-to-video translation model that decomposes the style and the content, uses the specialized encoder-decoder structure and propagates the inter-frame information through bidirectional recurrent neural network (RNN) units, enables to achieve style consistent video translation results.
- Improving Facial Attribute Recognition by Group and Graph Learning12
A unified network called Multi-scale Group and Graph Network is proposed that incorporates these two newly proposed learning strategies and produces coarse-to-fine graph-based group features for improving facial attribute recognition.
- 12
- Robust Message Embedding via Attention Flow-Based Steganography11
A novel message embedding framework, called Robust Message Steganography (RMSteg), which is competent to hide message via QR Code in a host image based on an normalizing flow-based model and is the first work that integrates the advantages of transformer models into normalizing flow.
- Stereo Risk: A Continuous Modeling Approach to Stereo Matching10
Stereo Risk is introduced, a new deep-learning approach to solve the classical stereo-matching problem in computer vision by formulating the scene disparity as an optimal solution to a continuous risk minimization problem, hence the name.
- Inductive Gradient Adjustment For Spectral Bias In Implicit Neural Representations10
This paper proposes a practical Inductive Gradient Adjustment (IGA) method, which could purposefully improve the spectral bias via inductive generalization of eNTK-based gradient transformation matrix and evaluates the method on different INRs tasks with various INR architectures and compare to existing training techniques.
- Deep Line Encoding for Monocular 3D Object Detection and Depth Prediction10
The deep line encoding is proposed to make better use of the line information in scenes and advances the state-of-the-art on KITTI single-image 3D object detection and depth prediction benchmarks.
- Online multi-layer dictionary pair learning for visual classification10
A multi-layer dictionary pair learning based classifier to enhance the image classification performance with the multi- layer structure and a nonlinear feature transform in each layer could accumulate stronger discrimination capability than the previous single-layer representation based classifiers.
- 10
- MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioning9
This work proposes Markovian Visual AutoRegressive modeling (MVAR), a novel autoregressive framework that introduces scale and spatial Markov assumptions to reduce the complexity of conditional probability modeling and introduces spatial-Markov attention, which restricts the attention of each token to a localized neighborhood of size k at corresponding positions on adjacent scales.
- Flexible Example-Based Image Enhancement with Task Adaptive Global Feature Self-guided Network7
This model outperforms the current state of the art in learning a single enhancement mapping, while having significantly fewer parameters than its competitors, and achieves even higher performance on learning multiple mappings simultaneously, by taking advantage of shared representations.
- 7
- The Heterogeneity Hypothesis: Finding Layer-Wise Dissimilated Network Architecture.6
The ``heterogeneity hypothesis'' is articulate: with the same training protocol, there exists a layer-wise dissimilated network architecture (LW-DNA) that can outperform the original network with regular channel configurations under lower level of model complexity.
- Efficient Trimmed Convolutional Arithmetic Encoding for Lossless Image Compression.6
This work proposes a trimmed convolutional network for arithmetic encoding (TCAE), which attains better compression ratio in lossless gray image compression, and can be adopted in CNN-based lossy image compression to achieve state-of-the-art rate-distortion performance with real-time encoding speed.
- 6
- Learning Pixel-Adaptive Multi-Layer Perceptrons for Real-Time Image Enhancement5
This work generates bilateral grids containing MLP parameters, where each pixel dynamically retrieves its unique transformation parameters and obtain a distinct MLP for color mapping based on spatial coordinates and intensity values, and proposes a novel grid decomposition strategy that categorizes MLP parameters into distinct types stored in separate subgrids.
- Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compression4
RDVQ is proposed, a unified framework that enables end-to-end RD optimization for VQ-based compression via a differentiable relaxation of the codebook distribution, allowing the entropy loss to directly shape the latent prior.
- IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting4
This work introduces a Depth Probability Boosting Unit (DPBU) that integrates epipolar attention maps produced by cascading warp operations in a multiplicative manner, and proposes IDESplat, which iteratively applies warp operations to boost depth probability estimation for accurate Gaussian mean prediction.
- Photo-Realistic and Robust Inpainting of Faces Using Refinement GANs4
This paper proposes, design and evaluates a refinement generative adversarial network (GAN), that is applied within an inpainting pipeline to robustly generate photo-realistic restorations and concludes, that refinement considerably improves for each setting the numerical and visual quality and preserves already good restoration.
- 4
- ATD: Improved Transformer With Adaptive Token Dictionary for Image Restoration3
Adaptive Token Dictionary is proposed, a novel transformer-based architecture for image restoration that enables global dependency modeling with linear complexity relative to image size and develops ATD-U, a multi-scale variant of ATD that achieves state-of-the-art performance on multiple image super-resolution benchmarks.
- Neural Stereo Video Compression With Hybrid Disparity Compensation3
A hybrid disparity compensation (HDC) strategy that leverages explicit pixel displacement as a robust prior feature to simplify optimization and perform implicit cross-attention mechanisms for subsequent warping operations, thereby capturing a broader range of disparity information.
- Task-Aware Image Signal Processor for Advanced Visual Perception3
The proposed Task-Aware Image Signal Processing (TA-ISP), a compact RAW-to-RGB framework that produces task-oriented representations for pretrained vision models, predicts a small set of lightweight, multi-scale modulation operators that act at global, regional, and pixel scales to reshape image statistics across different spatial extents.
- 2
- Learning Unpaired Image Dehazing with Physics-based Rehazy Generation2
This paper proposes a novel training strategy for unpaired image dehazing, termed Rehazy, to improve both dehazing performance and training stability and introduces a dual-branch framework for dehazing network training, which progressively restores clean scenes from coarse to fine.
- 2
- Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models1
This work proposes a simple yet effective solution that constructs a latent space robust to sampling perturbations while maintaining strong reconstruction fidelity, and introduces a Variance Expansion loss that counteracts variance collapse and leverages the adversarial interplay between reconstruction and variance expansion to achieve an adaptive balance.
- Generative Image Compression by Estimating Gradients of the Rate-variable Feature Distribution1
This paper proposes a novel diffusion-based generative modeling framework tailored for generative image compression that outperforms existing generative image compression approaches across a range of metrics, including perceptual distortion, statistical fidelity, and no-reference quality assessments.
- –
- –
- –
- –
- –
- Progressive Focused Transformer for Image Restoration–
The second version of Progressive Focused Transformer (PFTv2) is proposed which links all isolated attention maps in the network through Progressive Focused Attention (PFA), arguing that leveraging the information of attention maps across different layers is helpful for a comprehensive measurement of token similarity.
- –
- –
- DASR+: Training Domain Distance Aware Network for Unsupervised Image Super-Resolution–
A novel domain distance aware super-resolution (DASR+) approach with newly designed domain gap aware training strategy, domain distance weighted supervision strategy, and a domain distance adaptive network for unsupervised image super-resolution that outperforms state-of-the-art unsupervised SR methods in generating results with more realistic textures.
- –
- –
- –
- –
- HiLLIE: Human-in-the-Loop Training for Low-Light Image Enhancement–
A human-in-the-loop LLIE training framework that improves the visual quality of unsupervised LLIE model outputs through iterative training stages, named HiLLIE, and continually improves the IQA model's capability to simulate human visual assessment of enhanced outputs, thus leading to visually appealing LLIE results.
- Small Clips, Big Gains: Learning Long-Range Refocused Temporal Information for Video Super-Resolution–
This work proposes LRTI-VSR, a novel training framework for recurrent VSR that efficiently leverages Long-Range Refocused Temporal Information and introduces a refocused intra&inter-frame transformer block which allows the VSR model to selectively prioritize useful temporal information through its attention module while further improving inter-frame information utilization in the FFN module.
- BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensation–
BasicAVSR significantly outperforms existing methods in terms of super-resolution quality, generalization ability, and inference speed and extends its core components to multiple frameworks for diverse scenarios.
- –
- –
- Special Section Guest Editorial: Perceptually Optimized Imaging–
This guest editorial summarizes the Special Section on Perceptually Optimized Imaging and describes the current state of the art in perception-based image-guided medicine.
- –
- Sparse and low-rank models for image restoration–
This work states that the sparse representation based methods have achieved a great success in image restoration in the last decade, but the projective coding mechanism of ASR based methods restrict their capacity of benefiting from highly redundant dictionaries, limiting their flexibility in modeling image complex texture structures.
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.