In image restoration (IR), leveraging semantic priors from segmentation models has been a common approach to improve performance. The recent segment anything model (SAM) has emerged as a powerful tool for extracting advanced semantic priors to enhance IR tasks. However, the computational cost of SAM is prohibitive for IR, compared to existing smaller IR models. The incorporation of SAM for extracting semantic priors considerably hampers the model inference efficiency. To address this issue, we propose a general framework to distill SAM's semantic knowledge to boost exiting IR models without interfering with their inference process. Specifically, our proposed framework consists of the semantic priors fusion (SPF) scheme and the semantic priors distillation (SPD) scheme. SPF fuses two kinds of information between the restored image predicted by the original IR model and the semantic mask predicted by SAM for the refined restored image. SPD leverages a self-distillation manner to distill the fused semantic priors to boost the performance of original IR models. Additionally, we design a semantic-guided relation (SGR) module for SPD, which ensures semantic feature representation space consistency to fully distill the priors. We demonstrate the effectiveness of our framework across multiple IR models and tasks, including deraining, deblurring, and denoising.
Northwestern Polytechnical University（西北工业大学）；The University of Adelaide（阿德莱德大学）
In dynamic scenes, images often suffer from dynamic blur due to superposition of motions or low signal-noise ratio resulted from quick shutter speed when avoiding motions. Recovering sharp and clean results from the captured images heavily depends on the ability of restoration methods and the quality of the input. Although existing research on image restoration focuses on developing models for obtaining better restored results, fewer have studied to evaluate how and which input image leads to superior restored quality. In this paper, to better study an image's potential value that can be explo…
Almost all existing methods for image restoration are based on optimizing the mean squared error (MSE), even though it is known that the best estimate in terms of MSE may yield a highly atypical image due to the fact that there are many plausible restorations for a given noisy image. In this paper, we show how to combine explicit priors on patches of natural images in order to sample from the posterior probability of a full image given a degraded image. We prove that our algorithm generates correct samples from the distribution $p(x|y) \propto \exp(-E(x|y))$ where $E(x|y)$ is the cost function…
Instituto de Telecomunicações（电信研究所）；Instituto Superior Técnico, University of Lisbon（里斯本大学高等技术学院）
This paper introduces a new approach to patch-based image restoration based on external datasets and importance sampling. The Minimum Mean Squared Error (MMSE) estimate of the image patches, the computation of which requires solving a multidimensional (typically intractable) integral, is approximated using samples from an external dataset. The new method, which can be interpreted as a generalization of the external non-local means (NLM), uses self-normalized importance sampling to efficiently approximate the MMSE estimates. The use of self-normalized importance sampling endows the proposed met…
Distribution-aware Dataset Distillation for Efficient Image Restoration
Sun Yat‑sen University（中山大学）；Fuzhou University（福州大学）；University of Science and Technology of China（中国科学技术大学）；Nanjing University of Science and Technology（南京理工大学）
Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks. However, most prevalent deep learning models perform inference statically, ignoring that different images have varying restoration difficulties and lightly degraded images can be well restored by slimmer subnetworks. To this end, we propose a new solution pipeline dubbed ClassPruning that utilizes networks with different capabilities to process images with varying restoration difficulties. In particular, we use a lightweight classifier to identify the image restoration …
Also recently, exciting strides forward have been made in the area of image restoration, particularly for image denoising and single image super-resolution. Deep learning techniques contributed to this significantly. The top methods differ in their formulations and assumptions, so even if their average performance may be similar, some work better on certain image types and image regions than others. This complementarity motivated us to propose a novel 3D convolutional fusion (3DCF) method. Unlike other methods adapted to different tasks, our method uses the exact same convolutional network arc…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research（微软研究院）；University of Rochester（罗切斯特大学）
An important scenario for image quality assessment (IQA) is to evaluate image restoration (IR) algorithms. The state-of-the-art approaches adopt a full-reference paradigm that compares restored images with their corresponding pristine-quality images. However, pristine-quality images are usually unavailable in blind image restoration tasks and real-world scenarios. In this paper, we propose a practical solution named degraded-reference IQA (DR-IQA), which exploits the inputs of IR models, degraded images, as references. Specifically, we extract reference information from degraded images by dist…
Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey
School of Mathematical Sciences, Dalian University of Technology（大连理工大学数学科学学院）；Centre for Advances in Reliability and Safety, Hong Kong, China（香港可靠性与安全中心）；Hong Kong Polytechnic University（香港理工大学）；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）
This paper presents a scalable approximate Bayesian method for image restoration using total variation (TV) priors. In contrast to most optimization methods based on maximum a posteriori estimation, we use the expectation propagation (EP) framework to approximate minimum mean squared error (MMSE) estimators and marginal (pixel-wise) variances, without resorting to Monte Carlo sampling. For the classical anisotropic TV-based prior, we also propose an iterative scheme to automatically adjust the regularization parameter via expectation-maximization (EM). Using Gaussian approximating densities wi…
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shanghai AI Laboratory（上海人工智能实验室）；The Hong Kong Polytechnic University（香港理工大学）；ARC Lab, Tencent PCG（腾讯平台与内容事业群ARC实验室）；The Chinese University of Hong Kong（香港中文大学）
Transform image processing methods are methods that work in domains of image transforms, such as Discrete Fourier, Discrete Cosine, Wavelet and alike. They are the basic tool in image compression, in image restoration, in image re-sampling and geometrical transformations and can be traced back to early 1970-ths. The paper presents a review of these methods with emphasis on their comparison and relationships, from the very first steps of transform image compression methods to adaptive and local adaptive transform domain filters for image restoration, to methods of precise image re-sampling and …
Perceive-IR: Learning to Perceive Degradation Better for All-in-One Image Restoration
National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University（国家多媒体软件工程研究中心，计算机学院，武汉大学）；School of Computer Science, Wuhan University（计算机学院，武汉大学）；Horizon Robotics（_horizon robotics）；School of Information Engineering, Guangdong University of Technology（信息工程学院，广东技术大学）
This paper presents a new Expectation Propagation (EP) framework for image restoration using patch-based prior distributions. While Monte Carlo techniques are classically used to sample from intractable posterior distributions, they can suffer from scalability issues in high-dimensional inference problems such as image restoration. To address this issue, EP is used here to approximate the posterior distributions using products of multivariate Gaussian densities. Moreover, imposing structural constraints on the covariance matrices of these densities allows for greater scalability and distribute…
Progressive Image Restoration via Text-Conditioned Video Generation
Department of Computer Science, University of Illinois Springfield（伊利诺伊大学斯普林菲尔德分校计算机科学系）；School of Electrical and Computer Engineering, Purdue University（普渡大学电气与计算机工程学院）
NVIDIA AI Technology Center（英伟达人工智能技术中心）；National Taiwan Normal University（台湾师范大学）
Speckle noise is an inherent disturbance in coherent imaging systems such as digital holography, synthetic aperture radar, optical coherence tomography, or ultrasound systems. These systems usually produce only single observation per view angle of the same interest object, imposing the difficulty to leverage the statistic among observations. We propose a novel image restoration algorithm that can perform speckle noise removal without clean data and does not require multiple noisy observations in the same view angle. Our proposed method can also be applied to the situation without knowing the n…
Blind super-resolution (SR) aims to recover high-quality visual textures from a low-resolution (LR) image, which is usually degraded by down-sampling blur kernels and additive noises. This task is extremely difficult due to the challenges of complicated image degradations in the real-world. Existing SR approaches either assume a predefined blur kernel or a fixed noise, which limits these approaches in challenging cases. In this paper, we propose a Degradation-guided Meta-restoration network for blind Super-Resolution (DMSR) that facilitates image restoration for real cases. DMSR consists of a …
ContiLNN: Mitigating Slice Sampling Discontinuity with Liquid Neural Networks for Medical Image Restoration
Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；Academy of Artificial Intelligence and Advanced Technology, Xi’an Jiaotong-Liverpool University（西交利物浦大学人工智能与先进技术研究院）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
University of Bern（伯尔尼大学）；University of Maryland, College Park（马里兰大学学院市分校）
We propose to leverage denoising autoencoder networks as priors to address image restoration problems. We build on the key observation that the output of an optimal denoising autoencoder is a local mean of the true data density, and the autoencoder error (the difference between the output and input of the trained autoencoder) is a mean shift vector. We use the magnitude of this mean shift vector, that is, the distance to the local mean, as the negative log likelihood of our natural image prior. For image restoration, we maximize the likelihood using gradient descent by backpropagating the auto…
This work presents an unsupervised deep learning scheme that exploiting high-dimensional assisted score-based generative model for color image restoration tasks. Considering that the sample number and internal dimension in score-based generative model have key influence on estimating the gradients of data distribution, two different high-dimensional ways are proposed: The channel-copy transformation increases the sample number and the pixel-scale transformation decreases feasible space dimension. Subsequently, a set of high-dimensional tensors represented by these transformations are used to t…
Taiyuan University of Technology（太原理工大学）；Durham University（杜伦大学）
Texture is one of the most obvious characteristics in solar images and it is normally described by texture features. Because textures from solar images of the same wavelength are similar, we assume texture features of solar images are multi-fractals. Based on this assumption, we propose a pure data-based image restoration method: with several high resolution solar images as references, we use the Cycle-Consistent Adversarial Network to restore burred images of the same steady physical process, in the same wavelength obtained by the same telescope. We test our method with simulated and real obs…
Many interesting tasks in image restoration can be cast as linear inverse problems. A recent family of approaches for solving these problems uses stochastic algorithms that sample from the posterior distribution of natural images given the measurements. However, efficient solutions often require problem-specific supervised training to model the posterior, whereas unsupervised methods that are not problem-specific typically rely on inefficient iterative methods. This work addresses these issues by introducing Denoising Diffusion Restoration Models (DDRM), an efficient, unsupervised posterior sa…
Universität Innsbruck（因斯布鲁克大学）；Universität Graz（格拉茨大学）；Research Center for Non Destructive Testing GmbH（非破坏性测试研究中心 GmbH）；Prospective Instruments LK OG（前瞻性仪器 LK OG）
Decoupled Data Consistency with Diffusion Purification for Image Restoration
Department of Electrical Engineering and Computer Science, University of Michigan（电气工程与计算机科学系，密歇根大学）；Departments of Computational Mathematics, Science and Engineering, and Biomedical Engineering, Michigan State University（计算数学、科学与工程系，以及生物医学工程系，密歇根州立大学）
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Science and Technology of China（中国科学技术大学）
Person re-identification (reID) is an important task that requires to retrieve a person's images from an image dataset, given one image of the person of interest. For learning robust person features, the pose variation of person images is one of the key challenges. Existing works targeting the problem either perform human alignment, or learn human-region-based representations. Extra pose information and computational cost is generally required for inference. To solve this issue, a Feature Distilling Generative Adversarial Network (FD-GAN) is proposed for learning identity-related and pose-unre…
The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Laboratory（上海人工智能实验室）；Nanyang Technological University（南洋理工大学）
StyleGAN family is one of the most popular Generative Adversarial Networks (GANs) for unconditional generation. Despite its impressive performance, its high demand on storage and computation impedes their deployment on resource-constrained devices. This paper provides a comprehensive study of distilling from the popular StyleGAN-like architecture. Our key insight is that the main challenge of StyleGAN distillation lies in the output discrepancy issue, where the teacher and student model yield different outputs given the same input latent code. Standard knowledge distillation losses typically f…
Distilling Vision Transformers for Distortion-Robust Representation Learning
Department of Informatics and Telecommunications, National and Kapodistrian University of Athens, Greece（希腊雅典国家与卡波迪斯蒂亚纳大学信息与电信系）；National Observatory of Athens, Greece（希腊雅典国家天文台）；Information Management Systems Institute, Athena Research Center, Greece（希腊阿提卡研究中心信息管理系统研究所）
Equivariant Sampling for Improving Diffusion Model-based Image Restoration
School of Biomedical Engineering, Division of Life Sciences and Medicine, USTC（生物医学工程学院，生命科学与医学系，中国科学技术大学）；MIRACLE Center, Suzhou Institute for Advance Research, USTC（MIRACLE中心，苏州市先进研究院，中国科学技术大学）；Key Laboratory of Intelligent Information Processing of CAS, ICT, CAS（中国科学院智能信息处理重点实验室，ICT，中国科学院）；State Key Laboratory of Precision and Intelligent Chemistry, USTC（中国科学技术大学精密与智能化学国家重点实验室）
One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models
Nankai University（南开大学）；Guizhou Normal University（贵州师范大学）；Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；SoftBank（软银）；Nankai International Advanced Research Institute (Shenzhen Futian)（南开国际先进研究院（深圳福田））
City University of Hong Kong（香港城市大学）；Microsoft Research Asia（微软亚洲研究院）
Recent progress in contrastive learning has revolutionized unsupervised representation learning. Concretely, multiple views (augmentations) from the same image are encouraged to map to the similar embeddings, while views from different images are pulled apart. In this paper, through visualizing and diagnosing classification errors, we observe that current contrastive models are ineffective at localizing the foreground object, limiting their ability to extract discriminative high-level features. This is due to the fact that view generation process considers pixels in an image uniformly. To addr…
From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation
Malaviya National Institute of Technology, Jaipur, India（马利瓦国家理工学院，印度斋普尔）；Côte d’Azur University, France（蔚蓝海岸大学，法国）；University of South Dakota, USA（南达科他大学，美国）
WaveDM: Wavelet-Based Diffusion Models for Image Restoration
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；The University of Hong Kong（香港大学）
Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward
The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；Snap Research；Shenzhen University（深圳大学）；HKUST（香港科技大学）；University of Central Florida（佛罗里达大学）；UC Davis（加州大学戴维斯分校）；Sun Yat-Sen University（孙中山大学）
