HAT: Hybrid Attention Transformer for Image Restoration
State Key Laboratory of Internet of Things for Smart City, University of Macau（澳门大学物联网智能城市国家重点实验室）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；ARC Lab, Tencent PCG（腾讯PCG ARC实验室）
Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better restoration, we propose a new Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to further exploit the potential of the model for further improvement. Extensive experiments have demonstrated the effectiveness of the proposed modules. We further scale up the model to show that the performance of the SR task can be greatly improved. Besides, we extend HAT to more image restoration applications, including real-world image super-resolution, Gaussian image denoising and image compression artifacts reduction. Experiments on benchmark and real-world datasets demonstrate that our HAT achieves state-of-the-art performance both quantitatively and qualitatively. Codes and models are publicly available at https://github.com/XPixelGroup/HAT.
Xinjiang University（新疆大学）；Shandong University of Technology（山东理工大学）
Although Convolutional Neural Networks (CNN) have made good progress in image restoration, the intrinsic equivalence and locality of convolutions still constrain further improvements in image quality. Recent vision transformer and self-attention have achieved promising results on various computer vision tasks. However, directly utilizing Transformer for image restoration is a challenging task. In this paper, we introduce an effective hybrid architecture for sand image restoration tasks, which leverages local features from CNN and long-range dependencies captured by transformer to improve the r…
While Transformer has achieved remarkable performance in various high-level vision tasks, it is still challenging to exploit the full potential of Transformer in image restoration. The crux lies in the limited depth of applying Transformer in the typical encoder-decoder framework for image restoration, resulting from heavy self-attention computation load and inefficient communications across different depth (scales) of layers. In this paper, we present a deep and effective Transformer-based network for image restoration, termed as U2-Former, which is able to employ Transformer as the core oper…
University of Science and Technology of China（中国科学技术大学）
We propose a novel zero-shot multi-frame image restoration method for removing unwanted obstruction elements (such as rains, snow, and moire patterns) that vary in successive frames. It has three stages: transformer pre-training, zero-shot restoration, and hard patch refinement. Using the pre-trained transformers, our model is able to tell the motion difference between the true image information and the obstructing elements. For zero-shot image restoration, we design a novel model, termed SiamTrans, which is constructed by Siamese transformers, encoders, and decoders. Each transformer has a te…
University of Science and Technology of China（中国科学技术大学）；University of Macau（澳门大学）；University of Chinese Academy of Sciences（中国科学院大学）
In this paper, we present Uformer, an effective and efficient Transformer-based architecture for image restoration, in which we build a hierarchical encoder-decoder network using the Transformer block. In Uformer, there are two core designs. First, we introduce a novel locally-enhanced window (LeWin) Transformer block, which performs nonoverlapping window-based self-attention instead of global self-attention. It significantly reduces the computational complexity on high resolution feature map while capturing local context. Second, we propose a learnable multi-scale restoration modulator in the…
Inception Institute of AI（人工智能起源研究所）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Monash University（莫纳什大学）；University of California, Merced（加州大学默塞德分校）；Yonsei University（延世大学）；Google Research（谷歌研究院）
Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks. Recently, another class of neural architectures, Transformers, have shown significant performance gains on natural language and high-level vision tasks. While the Transformer model mitigates the shortcomings of CNNs (i.e., limited receptive field and inadaptability to input content), its computational complexity grows quadratically with the spatial resolution, therefore making it infeasible to ap…
Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs. However, how to efficiently leverage such architectures remains an open problem. In this work, we present Dual-former whose critical insight is to combine the powerful global modeling ability of self-attention modules and the local modeling ability of convolutions in an overall architecture. With convolution-based Local Feature Extraction modules equipped in the encoder and the decoder, we only adopt a novel Hybrid Transformer Block in the latent layer to model the long-distance d…
Shanghai Jiao Tong University（上海交通大学）；ETH Zürich（苏黎世联邦理工学院）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Sydney（悉尼大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Westlake University（西湖大学）
Recently, Transformer architecture has been introduced into image restoration to replace convolution neural network (CNN) with surprising results. Considering the high computational complexity of Transformer with global attention, some methods use the local square window to limit the scope of self-attention. However, these methods lack direct interaction among different windows, which limits the establishment of long-range dependencies. To address the above issue, we propose a new image restoration model, Cross Aggregation Transformer (CAT). The core of our CAT is the Rectangle-Window Self-Att…
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Hong Kong University of Science and Technology（香港科技大学）；Rakuten Institute of Technology（乐天理工研究院）；Imperial College London（伦敦帝国学院）；KAIST（韩国科学技术院）；Tencent（腾讯）；Australian National University（澳大利亚国立大学）；Nanjing University（南京大学）
Due to various and complicated snow degradations, single image desnowing is a challenging image restoration task. As prior arts can not handle it ideally, we propose a novel transformer, SnowFormer, which explores efficient cross-attentions to build local-global context interaction across patches and surpasses existing works that employ local operators or vanilla transformers. Compared to prior desnowing methods and universal image restoration methods, SnowFormer has several benefits. Firstly, unlike the multi-head self-attention in recent image restoration Vision Transformers, SnowFormer inco…
TDiR: Transformer based Diffusion for Image Restoration Tasks
Department of Computer Vision（计算机视觉系）；FutureDataMinds；Electrical Engineering Dept（电气工程系）；King Fahd University of Petroleum and Minerals（国王法赫德石油和矿产大学）；Department of Computer Science and Software Engineering（计算机科学与软件工程系）；University of Western Australia（西澳大学）；School of Computing（计算学院）
National University of Defense Technology（国防科技大学）；National Innovation Institute of Defense Technology（国防科技创新研究院）
The great success of Deep Neural Networks (DNNs) has inspired the algorithmic development of DNN-based Fixed-Point (DNN-FP) for computer vision tasks. DNN-FP methods, trained by Back-Propagation Through Time or computing the inaccurate inversion of the Jacobian, suffer from inferior representation ability. Motivated by the representation power of the Transformer, we propose a framework to unroll the FP and approximate each unrolled process via Transformer blocks, called FPformer. To reduce the high consumption of memory and computation, we come up with FPRformer by sharing parameters between t…
Shanghai Jiao Tong University（上海交通大学）；ETH Zürich（苏黎世联邦理工学院）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Sydney（悉尼大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Westlake University（西湖大学）
Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit self-attention computation within non-overlapping windows. However, each group of tokens are always from a dense area of the image. This is considered as a dense attention strategy since the interactions of tokens are restrained in dense regions. Obviously, this strategy could result in restricted receptive fields. To address this issue, we propose Attention Re…
Enhancing Image Restoration Transformer via Adaptive Translation Equivariance
Institute of Medical Technology, Peking University Health Science Center, Peking University（北京大学医学部医学技术研究所）；Biomedical Engineering Department, College of Future Technology, Peking University（未来技术学院生物医学工程系）；National Biomedical Imaging Center, Peking University（北京大学国家生物医学成像中心）；China Mobile Research Institute（中国移动研究院）
Joint multi-dimensional dynamic attention and transformer for general image restoration
School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院）；Key Laboratory of Photonic Technology for Integrated Sensing and Communication, Ministry of Education（教育部光子技术集成感知与通信重点实验室）；Guangdong Provincial Key Laboratory of Information Photonics Technology（广东省信息光子技术重点实验室）；Institute of Advanced Photonics Technology, School of Information Engineering, Guangdong University of Technology（广东工业大学信息工程学院先进光子技术研究所）；School of Electronics and Communication Engineering, Sun Yat-Sen University（中山大学电子与通信工程学院）
Intra and Inter Parser-Prompted Transformers for Effective Image Restoration
Sun Yat-sen University（中山大学）；Centre for Advances in Reliability and Safety（可靠性与安全先进中心）；The Hong Kong Polytechnic University（香港理工大学）；Nanjing University of Science and Technology（南京理工大学）；Dalian University of Technology（大连理工大学）
In order to get raw images of high quality for downstream Image Signal Process (ISP), in this paper we present an Efficient Locally Multiplicative Transformer called ELMformer for raw image restoration. ELMformer contains two core designs especially for raw images whose primitive attribute is single-channel. The first design is a Bi-directional Fusion Projection (BFP) module, where we consider both the color characteristics of raw images and spatial structure of single-channel. The second one is that we propose a Locally Multiplicative Self-Attention (L-MSA) scheme to effectively deliver infor…
Multi-dimensional Visual Prompt Enhanced Image Restoration via Mamba-Transformer Aggregation
School of Digital Industry, Jiangxi Normal University（江西师范大学数字产业学院）；School of Computer and Information Engineering, Jiangxi Normal University（江西师范大学计算机与信息工程学院）
MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration
School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区智能系统工程学院）；Guangdong Provincial Key Laboratory of Fire Science and Technology（广东省火灾科学与技术重点实验室）；School of Computer Science and Technology, Shenzhen Campus of Harbin Institute of Technology（哈尔滨工业大学深圳校区计算机科学与技术学院）；School of Engineering and Computer Science, Australian National University（澳大利亚国立大学工程与计算机科学学院）；Hong Kong University of Science and Technology（香港科技大学）
How Powerful Potential of Attention on Image Restoration?
Sun Yat-sen University（中山大学）；The Hong Kong Polytechnic University（香港理工大学）；Nanjing University of Science and Technology（南京理工大学）；National University of Singapore（新加坡国立大学）；Dalian University of Technology（大连理工大学）
ATD: Improved Transformer with Adaptive Token Dictionary for Image Restoration
School of Computer Science and Engineering (School of Cyber Security), University of Electronic Science and Technology of China (UESTC)（计算机科学与工程学院（网络安全学院），电子科学与技术大学（UESTC））
Look-Around Before You Leap: High-Frequency Injected Transformer for Image Restoration
College of Computer Science, Nankai University（南开大学计算机学院）；Nankai International Advanced Research Institute（南开大学国际高等研究院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）
Neural Discrimination-Prompted Transformers for Efficient UHD Image Restoration and Enhancement
Shenzhen Campus of Sun Yat-Sen University（中山大学深圳校区）；The Hong Kong Polytechnic University（香港理工大学）；Nanjing University of Science and Technology（南京理工大学）；Dalian University of Technology（大连理工大学）；University of California, San Francisco（加州大学旧金山分校）
Ultra-High-Definition Restoration Transformers with Correlation Matching Transformation
University of California, San Francisco（加利福尼亚大学旧金山分校）；School of Mathematical Sciences, Dalian University of Technology（大连理工大学数学科学学院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Computing and Communications, Lancaster University（兰卡斯特大学计算与通信学院）
Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image recons…
Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration
College of Computer Science, Nankai University（南开大学计算机学院）；Nankai International Advanced Research Institute（南开大学国际高等研究院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）
Sharing Key Semantics in Transformer Makes Efficient Image Restoration
ETH Zürich（苏黎世联邦理工学院）；INSAIT, Sofia University（保加利亚索菲亚大学INSAIT研究院）；University of Pisa（比萨大学）；University of Trento（特伦托大学）；Meta Reality Labs（元宇宙现实实验室）；Peking University（北京大学）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）；University of California, Merced（加州大学默塞德分校）
Correlation Matching Transformation Transformers for UHD Image Restoration
The Hong Kong Polytechnic University（香港理工大学）；Nanjing University of Science and Technology（南京理工大学）；Dalian University of Technology（大连理工大学）；National University of Singapore（新加坡国立大学）；Hebei University of Technology（河北工业大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Training-Free Large Model Priors for Multiple-in-One Image Restoration
Hefei Institutes of Physical Science, Chinese Academy of Sciences（中国科学院合肥物质科学研究院）；University of Science and Technology of China（中国科学技术大学）；Xiamen University（厦门大学）
Segmentation Guided Sparse Transformer for Under-Display Camera Image Restoration
Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；Hong Kong University of Science and Technology（香港科技大学）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；Samsung Research China - Beijing (SRC-B)（三星中国研究院北京分部）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳校区）；SAMSUNG Electronics（三星电子）
Dual Prompting Image Restoration with Diffusion Transformers
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学网络科学与技术学院）；MoE Key Laboratory of Information Technology（信息科技联合实验室）；Huawei Noah’s Ark Lab（华为诺亚实验室）；The Chinese University of Hong Kong（香港中文大学）；Guangdong Provincial Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）
ETH Zurich（苏黎世联邦理工学院）；Meta Inc.（Meta公司）；KU Leuven（鲁汶大学）
Video restoration (e.g., video super-resolution) aims to restore high-quality frames from low-quality frames. Different from single image restoration, video restoration generally requires to utilize temporal information from multiple adjacent but usually misaligned video frames. Existing deep methods generally tackle with this by exploiting a sliding window strategy or a recurrent architecture, which either is restricted by frame-by-frame restoration or lacks long-range modelling ability. In this paper, we propose a Video Restoration Transformer (VRT) with parallel frame prediction and long-ra…
University of Würzburg（维尔茨堡大学）；MegaStudyEdu（MegaStudy教育）
Compression plays an important role on the efficient transmission and storage of images and videos through band-limited systems such as streaming services, virtual reality or videogames. However, compression unavoidably leads to artifacts and the loss of the original information, which may severely degrade the visual quality. For these reasons, quality enhancement of compressed images has become a popular research topic. While most state-of-the-art image restoration methods are based on convolutional neural networks, other transformers-based methods such as SwinIR, show impressive performance …
University of Science and Technology of China（中国科学技术大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；Huawei Cloud BU（华为云业务单元）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Macau（澳门大学）；Shenzhen Institutes of Advanced Technology, CAS（中国科学院深圳先进技术研究院）
Learning a generalized prior for natural image restoration is an important yet challenging task. Early methods mostly involved handcrafted priors including normalized sparsity, l_0 gradients, dark channel priors, etc. Recently, deep neural networks have been used to learn various image priors but do not guarantee to generalize. In this paper, we propose a novel approach that embeds a task-agnostic prior into a transformer. Our approach, named Task-Agnostic Prior Embedding (TAPE), consists of two stages, namely, task-agnostic pre-training and task-specific fine-tuning, where the first stage emb…
TAT: Task-Adaptive Transformer for All-in-One Medical Image Restoration
School of Biological Science and Medical Engineering（生物科学与医学工程学院）；State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）；Key Laboratory of Biomechanics and Mechanobiology of Ministry of Education（教育部生物力学与机力学重点实验室）；Beijing Advanced Innovation Center for Biomedical Engineering（北京生物医学工程先进创新中心）；Beihang University（北京航空航天大学）；Sinovision Technologies (Beijing) Co., Ltd.（北京视界科技有限公司）；ByteDance Inc.（字节跳动公司）
University of Pisa（比萨大学）；University of Trento（特伦托大学）；ETH Zürich（苏黎世联邦理工学院）；Meta Reality Labs（元宇宙现实实验室）；Peking University（北京大学）；University of Modena and Reggio Emilia（摩德纳大学与雷焦艾米利亚大学）
