Global operations, such as global average pooling, are widely used in top-performance image restorers. They aggregate global information from input features along entire spatial dimensions but behave differently during training and inference in image restoration tasks: they are based on different regions, namely the cropped patches (from images) and the full-resolution images. This paper revisits global information aggregation and finds that the image-based features during inference have a different distribution than the patch-based features during training. This train-test inconsistency negatively impacts the performance of models, which is severely overlooked by previous works. To reduce the inconsistency and improve test-time performance, we propose a simple method called Test-time Local Converter (TLC). Our TLC converts global operations to local ones only during inference so that they aggregate features within local spatial regions rather than the entire large images. The proposed method can be applied to various global modules (e.g., normalization, channel and spatial attention) with negligible costs. Without the need for any fine-tuning, TLC improves state-of-the-art results on several image restoration tasks, including single-image motion deblurring, video deblurring, defocus deblurring, and image denoising. In particular, with TLC, our Restormer-Local improves the state-of-the-art result in single image deblurring from 32.92 dB to 33.57 dB on GoPro dataset. The code is available at https://github.com/megvii-research/tlc.
The Chinese University of Hong Kong（香港中文大学）；Smartmore Corporation（思谋科技）
Long-range temporal alignment is critical yet challenging for video restoration tasks. Recently, some works attempt to divide the long-range alignment into several sub-alignments and handle them progressively. Although this operation is helpful in modeling distant correspondences, error accumulation is inevitable due to the propagation mechanism. In this work, we present a novel, generic iterative alignment module which employs a gradual refinement scheme for sub-alignments, yielding more accurate motion compensation. To further enhance the alignment accuracy and temporal consistency, we devel…
Revisiting Global Token Mixing in Task-Dependent MRI Restoration: Insights from Minimal Gated CNN Baselines
Dept. of Radiology & Imaging Sciences, University of Utah, Salt Lake City, UT, USA（放射学与成像科学系，犹他大学，盐湖城，UT，USA）；Dept. of Electrical & Computer Engineering, University of Utah, Salt Lake City, UT, USA（电气与计算机工程系，犹他大学，盐湖城，UT，USA）；Dept. of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE（计算机视觉系，莫扎德人工智能大学，阿布扎赫，EUA）；Dept. of Biomedical Engineering, University of Utah, Salt Lake City, UT, USA（生物医学工程系，犹他大学，盐湖城，UT，USA）；Dept. of Electrical & Computer Engineering, University of Washington, Seattle, WA, USA（电气与计算机工程系，华盛顿大学，西雅图，WA，USA）
It is now well known that Markov random fields (MRFs) are particularly effective for modeling image priors in low-level vision. Recent years have seen the emergence of two main approaches for learning the parameters in MRFs: (1) probabilistic learning using sampling-based algorithms and (2) loss-specific training based on MAP estimate. After investigating existing training approaches, it turns out that the performance of the loss-specific training has been significantly underestimated in existing work. In this paper, we revisit this approach and use techniques from bi-level optimization to sol…
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…
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）
How to aggregate spatial information plays an essential role in learning-based image restoration. Most existing CNN-based networks adopt static convolutional kernels to encode spatial information, which cannot aggregate spatial information adaptively. Recent transformer-based architectures achieve adaptive spatial aggregation. But they lack desirable inductive biases of convolutions and require heavy computational costs. In this paper, we propose a kernel basis attention (KBA) module, which introduces learnable kernel bases to model representative image patterns for spatial information aggrega…
Image restoration is the task of recovering a clean image from a degraded version. In most cases, the degradation is spatially varying, and it requires the restoration network to both localize and restore the affected regions. In this paper, we present a new approach suitable for handling the image-specific and spatially-varying nature of degradation in images affected by practically occurring artifacts such as blur, rain-streaks. We decompose the restoration task into two stages of degradation localization and degraded region-guided restoration, unlike existing methods which directly learn a …
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）
CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, University of Science and Technology of China（中国科学技术大学 中国科学院空间信息处理与应用系统技术重点实验室）
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises the restoration performance. To decompose such interference, we introduce the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions. Specifically, we propose the feature disentanglement module (FDM) to distribute feature representations of different distortions into different channels by revising gain-…
Yonsei University（延世大学）；Chungnam National University（忠南国立大学）
Regularization-based image restoration has remained an active research topic in computer vision and image processing. It often leverages a guidance signal captured in different fields as an additional cue. In this work, we present a general framework for image restoration, called deeply aggregated alternating minimization (DeepAM). We propose to train deep neural network to advance two of the steps in the conventional AM algorithm: proximal mapping and ?- continuation. Both steps are learned from a large dataset in an end-to-end manner. The proposed framework enables the convolutional neural n…
ETH Zurich（苏黎世联邦理工学院）；Meta Inc.（Meta公司）；University of Wurzburg（维尔茨堡大学）
Video restoration aims at restoring multiple high-quality frames from multiple low-quality frames. Existing video restoration methods generally fall into two extreme cases, i.e., they either restore all frames in parallel or restore the video frame by frame in a recurrent way, which would result in different merits and drawbacks. Typically, the former has the advantage of temporal information fusion. However, it suffers from large model size and intensive memory consumption; the latter has a relatively small model size as it shares parameters across frames; however, it lacks long-range depende…
Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration
University of Mannheim（曼海姆大学）；Institute for Machine Learning and Analytics（机器学习与分析研究所）；Offenburg University（奥芬堡大学）；Max Planck Institute for Informatics（马克斯·普朗克信息研究所）；Saarland Informatics Campus（萨尔州信息校区）
Inception Institute of Artificial Intelligence（起源人工智能研究院）；Mohammed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of California at Merced（加州大学默塞德分校）；Google（谷歌）；Terminus Group（特斯联集团）
Given a degraded input image, image restoration aims to recover the missing high-quality image content. Numerous applications demand effective image restoration, e.g., computational photography, surveillance, autonomous vehicles, and remote sensing. Significant advances in image restoration have been made in recent years, dominated by convolutional neural networks (CNNs). The widely-used CNN-based methods typically operate either on full-resolution or on progressively low-resolution representations. In the former case, spatial details are preserved but the contextual information cannot be prec…
Hanyang University（汉阳大学）；LG AI Research（LG人工智能研究院）
Recent transformer-based super-resolution (SR) methods have achieved promising results against conventional CNN-based methods. However, these approaches suffer from essential shortsightedness created by only utilizing the standard self-attention-based reasoning. In this paper, we introduce an effective hybrid SR network to aggregate enriched features, including local features from CNNs and long-range multi-scale dependencies captured by transformers. Specifically, our network comprises transformer and convolutional branches, which synergetically complement each representation during the restor…
Nanjing University of Science and Technology（南京理工大学）；China Electronics Technology Group Corporation（中国电子科技集团有限公司）
Transformers-based methods have achieved significant performance in image deraining as they can model the non-local information which is vital for high-quality image reconstruction. In this paper, we find that most existing Transformers usually use all similarities of the tokens from the query-key pairs for the feature aggregation. However, if the tokens from the query are different from those of the key, the self-attention values estimated from these tokens also involve in feature aggregation, which accordingly interferes with the clear image restoration. To overcome this problem, we propose …
University of Science and Technology of China（中国科学技术大学）；Hong Kong University of Science and Technology（香港科技大学）；Shandong University（山东大学）；City University of Hong Kong（香港城市大学）；University of Central Florida（中佛罗里达大学）；Microsoft Cloud and AI（微软云与人工智能部门）
Image dehazing aims to recover the uncorrupted content from a hazy image. Instead of leveraging traditional low-level or handcrafted image priors as the restoration constraints, e.g., dark channels and increased contrast, we propose an end-to-end gated context aggregation network to directly restore the final haze-free image. In this network, we adopt the latest smoothed dilation technique to help remove the gridding artifacts caused by the widely-used dilated convolution with negligible extra parameters, and leverage a gated sub-network to fuse the features from different levels. Extensive ex…
Inception Institute of Artificial Intelligence（inception人工智能研究院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of California, Merced（加州大学默塞德分校）；Google Research（谷歌研究院）
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing. Recently, convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. Existing CNN-based methods typically operate either on full-resolution or on progressively low-resolution representations. In the former case, spatially precise but contextually less robust results are achieved, while in the latter case, sem…
Wuhan Institute of Technology（武汉工程大学）；Harbin Institute of Technology（哈尔滨工业大学）；Wuhan University（武汉大学）
Recently, face super-resolution (FSR) methods either feed whole face image into convolutional neural networks (CNNs) or utilize extra facial priors (e.g., facial parsing maps, facial landmarks) to focus on facial structure, thereby maintaining the consistency of the facial structure while restoring facial details. However, the limited receptive fields of CNNs and inaccurate facial priors will reduce the naturalness and fidelity of the reconstructed face. In this paper, we propose a novel paradigm based on the self-attention mechanism (i.e., the core of Transformer) to fully explore the represe…
Degradation-Aware Adaptive Context Gating for Unified Image Restoration
School of Computing and Artificial Intelligence, Southwest Jiaotong University（计算机与人工智能学院，西南交通大学）；Institute for Infocomm Research, Agency for Science, Technology and Research（信息通信研究院，科技研究局）；School of Computing and Artificial Intelligence, Jiangxi University of Finance and Economics（计算机与人工智能学院，江西财经大学）；School of Information Management, Jiangxi University of Finance and Economics（信息管理学院，江西财经大学）；Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education（可持续智慧城市交通工程研究中心，教育部）；National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University（综合交通运输大数据应用技术国家工程实验室，西南交通大学）
Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement
Indian Institute of Technology Ropar（印度理工学院鲁尔基分校）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of AI（起源人工智能研究院）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）
Nanyang Technological University（南洋理工大学）；Nokia Bell Labs（诺基亚贝尔实验室）；Institute of High Performance Computing, A*STAR（A*STAR高性能计算研究所）；University of Macau（澳门大学）；University of Electronic Science and Technology of China（电子科技大学）
Recent works that utilized deep models have achieved superior results in various image restoration applications. Such approach is typically supervised which requires a corpus of training images with distribution similar to the images to be recovered. On the other hand, the shallow methods which are usually unsupervised remain promising performance in many inverse problems, \eg, image compressive sensing (CS), as they can effectively leverage non-local self-similarity priors of natural images. However, most of such methods are patch-based leading to the restored images with various ringing arti…
Burstormer: Burst Image Restoration and Enhancement Transformer
Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Inception Institute of AI（Inception人工智能研究院）；Australian National University（澳大利亚国立大学）；Linköping University（林雪平大学）；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）
Nanyang Technological University（南洋理工大学）；Applied Research Center Tencent PCG（腾讯平台与内容事业群应用研究中心）；The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
Video super-resolution (VSR) approaches tend to have more components than the image counterparts as they need to exploit the additional temporal dimension. Complex designs are not uncommon. In this study, we wish to untangle the knots and reconsider some most essential components for VSR guided by four basic functionalities, i.e., Propagation, Alignment, Aggregation, and Upsampling. By reusing some existing components added with minimal redesigns, we show a succinct pipeline, BasicVSR, that achieves appealing improvements in terms of speed and restoration quality in comparison to many state-of…
Deep learning highly relies on the quantity of annotated data. However, the annotations for 3D volumetric medical data require experienced physicians to spend hours or even days for investigation. Self-supervised learning is a potential solution to get rid of the strong requirement of training data by deeply exploiting raw data information. In this paper, we propose a novel self-supervised learning framework for volumetric medical images. Specifically, we propose a context restoration task, i.e., Rubik's cube++, to pre-train 3D neural networks. Different from the existing context-restoration-b…
The University of Sydney（悉尼大学）；Sydney Neuroimaging Analysis Centre（悉尼神经影像分析中心）；NVIDIA Corporation（英伟达公司）
Federated learning (FL) has been widely employed for medical image analysis to facilitate multi-client collaborative learning without sharing raw data. Despite great success, FL's performance is limited for multiple sclerosis (MS) lesion segmentation tasks, due to variance in lesion characteristics imparted by different scanners and acquisition parameters. In this work, we propose the first FL MS lesion segmentation framework via two effective re-weighting mechanisms. Specifically, a learnable weight is assigned to each local node during the aggregation process, based on its segmentation perfo…
PCA-Seg: Revisiting Cost Aggregation for Open-Vocabulary Semantic and Part Segmentation
Nanjing University of Science and Technology（南京理工大学）；Nanjing Normal University（南京师范大学）；Department of Electrical and Computer Engineering, Sungkyunkwan University（成均馆大学电子与计算机工程系）；University of Electronic Science and Technology of China（电子科技大学）；State Key Laboratory of Intelligent Manufacturing of Advanced Construction Machinery（先进施工机械智能制造国家重点实验室）
EndoCaver: Handling Fog, Blur and Glare in Endoscopic Images via Joint Deblurring-Segmentation
1 CyPhi ( ) AI Research Lab, School of IT, Monash University, Malaysia Campus；2 Department of Electronic \& Computer Engineering, The Hong Kong University of Science；3 Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences
This paper presents a patch-wise low-rank based image denoising method with constrained variational model involving local and nonlocal regularization. On one hand, recent patch-wise methods can be represented as a low-rank matrix approximation problem whose convex relaxation usually depends on nuclear norm minimization (NNM). Here, we extend the NNM to the nonconvex schatten p-norm minimization with additional weights assigned to different singular values, which is referred to as the Weighted Schatten p-Norm Minimization (WSNM). An efficient algorithm is also proposed to solve the WSNM problem…
Multi-Scale Target-Aware Representation Learning for Fundus Image Enhancement
organization= Research Center for Translational Medicine, Medical Innovation Center；State Key Laboratory of Cardiology, Shanghai East Hospital , city= Shanghai , postcode= 200120 , country= China；organization= The Institute for Biomedical Engineering \& Nano Science, Tongji University School of Medicine , city= Shanghai , postcode= 200120 , country= China；organization= Shanghai Research Institute for Intelligent Autonomous Systems , city= Shanghai , postcode= 201210 , country= China；organization= Department of Ophthalmology, Tongji Hospital, School of Medicine, Tongji University , city= Shanghai , postcode= 200000 , country= China；organization= Ophthalmology, Isra Postgraduate Institute of Ophthalmology , city= Karachi , postcode= , country= Pakistan；organization= The Eye Centre, South City Hospital , city= Karachi , postcode= , country= Pakistan；organization= Center for the Development of Laboratory Equipment, Pakistan Council of Scientific；Industrial Research , city= Karachi , postcode= , country= Pakistan
