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
- Xiaoou TangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works105 from public data
- Image Super-Resolution Using Deep Convolutional Networks10,147
This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images, represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one.
- Learning a Deep Convolutional Network for Image Super-Resolution5,839
This work proposes a deep learning method for single image super-resolution (SR) that directly learns an end-to-end mapping between the low/high-resolution images and shows that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks4,943
This work thoroughly study three key components of SRGAN – network architecture, adversarial loss and perceptual loss, and improves each of them to derive an Enhanced SRGAN (ESRGAN), which achieves consistently better visual quality with more realistic and natural textures than SRGAN.
- Accelerating the Super-Resolution Convolutional Neural Network3,673
This paper aims at accelerating the current SRCNN, and proposes a compact hourglass-shape CNN structure for faster and better SR, and presents the parameter settings that can achieve real-time performance on a generic CPU while still maintaining good performance.
- Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data2,160
This work extends the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data and employs a U-Net discriminator with spectral normalization to increase discriminator capability and stabilize the training dynamics.
- 1,955
- EDVR: Video Restoration With Enhanced Deformable Convolutional Networks1,341
This work proposes a novel Video Restoration framework with Enhanced Deformable convolutions, termed EDVR, and proposes a Temporal and Spatial Attention (TSA) fusion module, in which attention is applied both temporally and spatially, so as to emphasize important features for subsequent restoration.
- Recovering Realistic Texture in Image Super-Resolution by Deep Spatial Feature Transform1,224
It is shown that it is possible to recover textures faithful to semantic classes in a single network conditioned on semantic segmentation probability maps through a novel Spatial Feature Transform (SFT) layer that generates affine transformation parameters for spatial-wise feature modulation.
- Activating More Pixels in Image Super-Resolution Transformer1,170
A novel Hybrid Attention Transformer (HAT) is proposed, which combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability.
- Compression Artifacts Reduction by a Deep Convolutional Network942
A compact and efficient network for seamless attenuation of different compression artifacts is formulated and it is demonstrated that a deeper model can be effectively trained with the features learned in a shallow network.
- BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond698
A succinct pipeline is shown that achieves appealing improvements in terms of speed and restoration quality in comparison to many state-of-the-art algorithms and can serve as strong baselines for future VSR approaches.
- Unsupervised Image Super-Resolution Using Cycle-in-Cycle Generative Adversarial Networks619
This work proposes a Cycle-in-Cycle network structure with generative adversarial networks (GAN) as the basic component to tackle the single image super-resolution problem in a more general case that the low-/high-resolution pairs and the down-sampling process are unavailable.
- Blind Super-Resolution With Iterative Kernel Correction591
An iterative correction scheme -- IKC that achieves better results than direct kernel estimation in blind SR problem and an effective SR network architecture using spatial feature transform (SFT) layers to handle multiple blur kernels, named SFTMD.
- Efficient Image Super-Resolution Using Pixel Attention474
This work designs a lightweight convolutional neural network for image super resolution with a newly proposed pixel attention scheme that could achieve similar performance as the lightweight networks - SRResNet and CARN, but with only 272K parameters.
- RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution412
This work first train a Ranker which can learn the behavior of perceptual metrics and then introduce a novel rank-content loss to optimize the perceptual quality, and shows that RankSRGAN achieves visually pleasing results and reaches state-of-the-art performance in perceptual metrics.
- Interpreting Super-Resolution Networks with Local Attribution Maps381
This work proposes a novel attribution approach called local attribution map (LAM), which inherits the integral gradient method yet with two unique features: one is to use the blurred image as the baseline input, and the other is to adopt the progressive blurring function as the path function.
- Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild372
This work introduces SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up, and develops a restoration-guided sampling method to suppress the fidelity issue encountered in generative-based restoration.
- 370
- 351
- PIPAL: A Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration320
It is indicated that existing IQA methods cannot fairly evaluate GAN-based IR algorithms, and a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) is contributed, which includes the results of GAn-based methods, which are missing in previous datasets.
- BeautyGAN283
A dual input/output Generative Adversarial Network that enables the network to learn translation on instance-level through unsupervised adversarial learning, and could generate visually pleasant makeup faces and accurate transferring results.
- Blueprint Separable Residual Network for Efficient Image Super-Resolution272
This paper proposes Blueprint Separable Residual Network (BSRN), a model containing two efficient designs, one of which is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation.
- Video super-resolution based on deep learning: a comprehensive survey235
This work comprehensively investigates 37 state-of-the-art VSR methods based on deep learning and proposes a taxonomy and classify the methods into seven sub-categories according to the ways of utilizing inter-frame information.
- Blind Image Super-Resolution: A Survey and Beyond228
A taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used to solve the SR model is proposed, which helps summarize and distinguish among existing methods.
- ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic223
A new solution pipeline that combines classification and SR in a unified framework that can help most existing methods save up to 50% FLOPs on DIV8K datasets and introduces a new classification method with two losses – Class-Loss and Average- Loss to produce the classification results.
- Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning221
In comparison to conventional human-designed networks, RL-Restore is capable of restoring images corrupted with complex and unknown distortions in a more parameter-efficient manner using the dynamically formed toolchain1.
- VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution216
An automatic and scalable pipeline to collect a high-quality video face dataset (VFHQ), which contains over 16, 000 high-fidelity clips of diverse interview scenarios, and shows that the temporal information plays a pivotal role in eliminating video consistency issues as well as further improving visual performance.
- SmartEdit: Exploring Complex Instruction-Based Image Editing with Multimodal Large Language Models213
A Bidirectional Interaction Module (BIM) is proposed that enables comprehensive bidirectional information interactions between the input image and the MLLM output and demonstrates that a small amount of complex instruction editing data can effectively stimulate SmartEdit’ s editing capabilities for more complex instructions.
- Understanding Deformable Alignment in Video Super-Resolution195
It is shown that deformable convolution can be decomposed into a combination of spatial warping and convolution, which reveals the commonality of deformable alignment and flow-based alignment in formulation, but with a key difference in their offset diversity.
- Teaching Large Language Models to Regress Accurate Image Quality Scores Using Score Distribution183
The distribution-based Depicted image Quality Assessment model for Score regression (DeQA-Score) is developed, showing that DeQA-Score stably outperforms baselines in score regression and can predict the score distribution that closely aligns with human annotations.
- HAT: Hybrid Attention Transformer for Image Restoration179
A new Hybrid Attention Transformer (HAT) is proposed that combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages, and achieves state-of-the-art performance both quantitatively and qualitatively.
- 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.
- Conditional Sequential Modulation for Efficient Global Image Retouching156
An extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching is proposed that achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively.
- 135
- HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization126
This work proposes a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction with denoising and dequantization, which achieves the state-of-the-art performance in quantitative comparisons and visual quality.
- 123
- 122
- Path-Restore: Learning Network Path Selection for Image Restoration118
The results show that Path-Restore, a multi-path CNN with a pathfinder that can dynamically select an appropriate route for each image region is effective for real-world denoising, where the noise distribution varies across different regions on a single image.
- Deep Network Interpolation for Continuous Imagery Effect Transition116
This work proposes a simple yet universal approach to attain a smooth control of diverse imagery effects in many low-level vision tasks, including image restoration, image-to-image translation, and style transfer through linear interpolation in the parameter space of two or more correlated networks.
- Modulating Image Restoration With Continual Levels via Adaptive Feature Modification Layers102
A unified CNN framework that consists of little additional parameters than a single-level model yet could handle arbitrary restoration levels between a start and an end level is proposed, and the properties of AdaFM layers are investigated, providing a detailed guidance on the usage of the proposed method.
- AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results101
The AIM 2020 challenge on efficient single image super-resolution was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images with focus on the proposed solutions and results.
- Enhanced Quadratic Video Interpolation100
This work improves the performance of QVI from three facets and proposes an enhanced quadratic video interpolation (EQVI) model that won the first place in the AIM2020 Video Temporal Super-Resolution Challenge and devise a novel multi-scale fusion network (MS-Fusion) which can be regarded as a learnable augmentation process.
- 99
- NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results94
The NTIRE 2022 challenge was to super-resolve an input image with a magnification factor of ×4 based on pairs of low and corresponding high resolution images and the aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics.
- GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors87
This work proposes a generative and controllable face SR framework, called GCFSR, which can re-construct images with faithful identity information without any additional priors and can outperform state-of-the-art methods for large upscalingfac-tors.
- NTIRE 2022 Challenge on Perceptual Image Quality Assessment84
This paper reports on the NTIRE 2022 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2022 to address the emerging challenge of IQA by perceptual image processing algorithms.
- 84
- A New Journey from SDRTV to HDRTV80
A lightweight network that utilizes global statistics as guidance to conduct image-adaptive color mapping and achieves state-of-the-art performance in quantitative comparisons and visual quality is presented.
- 72
- 71
- PS-NeRV: Patch-Wise Stylized Neural Representations for Videos69
This work proposes a patch-wise solution to represent a video with implicit neural representations, PS-NeRV, which represents videos as a function of patches and the corresponding patch coordinate, and achieves excellent reconstruction performance with fast decoding speed.
- Temporally consistent video colorization with deep feature propagation and self-regularization learning67
A novel temporally consistent video colorization (TCVC) framework that effectively propagates frame-level deep features in a bidirectional way to enhance the temporal consistency of colorization and introduces a self-regularization learning (SRL) scheme to minimize the differences in predictions obtained using different time steps.
- RankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank65
This work first train a Ranker which can learn the behaviour of perceptual metrics and then introduces a novel rank-content loss to optimize the perceptual quality, and extends the method to multiple Rankers to provide multi-dimension constraints for the generator.
- 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.
- RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization57
A new re-parameterizable block tailored for SR, namely RepSR, which consists of a clean residual path and two expand-and-squeeze convolution paths with the modified BN and can achieve a better trade-off between performance and actual running time than previous SR methods.
- Suppressing Model Overfitting for Image Super-Resolution Networks55
A simple learning principle MixUp is introduced to train networks on interpolations of sample pairs, which encourages networks to support linear behavior in-between training samples and this strategy proves to be successful in reducing the biases of data.
- 54
- Interactive Multi-dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration54
A new problem setup, called multi- dimension (MD) modulation, which aims at modulating output effects across multiple degradation types and levels, and a deep architecture - CResMD with newly introduced controllable residual connections for multi-dimension modulation is presented.
- OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer48
This paper designs a distortion-aware Transformer (OSRT) to modulate ERP distortions continuously and self-adaptively, and proposes Fisheye downsampling, which mimics the real-world imaging process and synthesizes more realistic low-resolution samples.
- 47
- 47
- Enhancing Descriptive Image Quality Assessment With a Large-Scale Multi-Modal Dataset45
Experimental results demonstrate that EDQA significantly outperforms traditional score-based methods, prior VLM-based IQA models, and proprietary GPT-4V in distortion identification, instant rating, and reasoning tasks.
- Harnessing Diffusion-Yielded Score Priors for Image Restoration45
HYPIR outperforms previous state-of-the-art methods, achieving efficient and high-quality image restoration, and inherits the capabilities of diffusion models with rich user control, enabling text-guided restoration and adjustable texture richness.
- 45
- A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds44
This work proposes a unified gated degradation model to generate a broad set of degradation cases using a random gate controller and proposes simple baseline networks that can effectively handle non-blind, classical, practical degradation cases as well as many other corner cases.
- Trinity of Pixel Enhancement: a Joint Solution for Demosaicking, Denoising and Super-Resolution.42
This paper proposes the Trinity Enhancement Network (TENet), a specially designed learning-based method for the mixture problem, which adopts a novel image processing pipeline order and a joint learning strategy, and contributes a new dataset namely PixelShift200, which consists of high-quality full color sampled real-world images using the advanced pixel shift technique.
- NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results41
This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video and proposed the LDV 2.0 dataset, which includes theLDV dataset (240 videos) and 95 additional videos.
- 41
- 40
- NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results40
This paper reviews the challenge on constrained high dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2022, and the competition set-up, datasets, proposed methods and their results.
- 37
- 37
- Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline35
This work comprehensively study the effects of pipelines on the mixture problem of learning-based DN, DM, and SR, in both sequential and joint solutions, and proposes an end-to-end Trinity Pixel Enhancement NETwork (TENet) that achieves the state-of-the-art performance for the mixture Problem.
- 35
- Evaluating the Generalization Ability of Super-Resolution Networks34
This work makes the first attempt to propose a Generalization Assessment Index for Super-Resolution (SR) networks, namely SRGA, which exploits the statistical characteristics of the internal features of deep networks to measure the generalization ability.
- Very Lightweight Photo Retouching Network With Conditional Sequential Modulation34
An extremely lightweight framework – Conditional Sequential Retouching Network (CSRNet) that achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively and can be easily extended to learn local enhancement effects.
- Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution31
This work introduces a novel approach to craft training degradation distributions using a small set of reference images based upon the binned representation of the degradation space and the Fr\'echet distance between degradation distributions.
- TextIR: A Simple Framework for Text-Based Editable Image Restoration30
A sophisticated framework enabling users to guide the restoration of deteriorated images via textual descriptions via textual descriptions is developed, and the text-image compatibility feature of CLIP enhances the integration of textual and visual data.
- 30
- AIM 2020 Challenge on Video Temporal Super-Resolution29
This paper reports the second AIM challenge on Video Temporal Super-Resolution (VTSR), a.k.a. frame interpolation, with a focus on the proposed solutions, results, and analysis, and proposes the enhanced quadratic video interpolation method.
- 26
- Learning A Low-Level Vision Generalist via Visual Task Prompt24
A Visual task Prompt-based Image Processing (VPIP) framework is proposed, which employs visual task prompts to manage tasks with different input-target domains and allows flexible selection of backbone network suitable for general tasks.
- Semantic-Sparse Colorization Network for Deep Exemplar-Based Colorization24
Semantic-Sparse Colorization Network (SSCN) is proposed to transfer both the global image style and detailed semantic-related colors to the gray-scale image in a coarse-to-fine manner and can perfectly balance the global and local colors while alleviating the ambiguous matching problem.
- Toward Interactive Modulation for Photo-Realistic Image Restoration22
A Controllable Unet Generative Adversarial Network (CUGAN) to generate high-frequency textures in the modulation tasks to achieve excellent performance on image restoration modulation tasks.
- Networks are Slacking Off: Understanding Generalization Problem in Image Deraining21
The experiments reveal that better generalization in a deraining network can be achieved by simplifying the complexity of the training background images, thereby suppressing overfitting the rain patterns and leading to improved generalization performance.
- Interpreting Low-Level Vision Models With Causal Effect Maps20
This work introduces causality theory to interpret low-level vision models and proposes a model-/task-agnostic method called Causal Effect Map (CEM), which can visualize and quantify the input-output relationships on either positive or negative effects.
- 17
- 14
- 13
- 12
- 10
- 8
- Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression7
This special issue covers the state of the art in learned image/video restoration and compression to promote further progress in innovative architectures and training methods for effective and efficient networks for image/video restoration and compression.
- Multi-Dimension Modulation for Image Restoration with Dynamic Controllable Residual Learning.7
The first MD modulation framework -- CResMD with newly introduced controllable residual connections is proposed, which adds a controlling variable on the conventional residual connection to allow a weighted summation of input and residual.
- Towards Efficient SDRTV-to-HDRTV by Learning From Image Formation5
This paper delineates and analyzes the SDRTV-to-HDRTV conversion by modeling the formation of SDRTV/HDRTV content, and proposes a new three-step solution called HDRTVNet++, which includes adaptive global color mapping, local enhancement, and highlight refinement.
- SimpleGVR: A Simple Baseline for Latent-Cascaded Video Super-Resolution5
This work establishes a simple yet effective baseline for cascaded video super-resolution generation, offering practical insights to guide future advancements in efficient cascaded synthesis systems.
- 4
- 3
- 2
- 2
- 2
- –
- Revisiting the generalization problem of low-level vision models through the lens of image deraining–
- –
- –
Publication data from OpenAlex; 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.