23 pages. Updated experiments and Fixed presentation issues. This is the journal version of arXiv:1909.08228; Code is available at: https://github.com/hkzhang91/HiNAS
Recently, much attention has been spent on neural architecture search (NAS), aiming to outperform those manually-designed neural architectures on high-level vision recognition tasks. Inspired by the success, here we attempt to leverage NAS techniques to automatically design efficient network architectures for low-level image restoration tasks. In particular, we propose a memory-efficient hierarchical NAS (termed HiNAS) and apply it to two such tasks: image denoising and image super-resolution. HiNAS adopts gradient based search strategies and builds a flexible hierarchical search space, including the inner search space and outer search space. They are in charge of designing cell architectures and deciding cell widths, respectively. For the inner search space, we propose a layer-wise architecture sharing strategy (LWAS), resulting in more flexible architectures and better performance. For the outer search space, we design a cell-sharing strategy to save memory, and considerably accelerate the search speed. The proposed HiNAS method is both memory and computation efficient. With a single GTX1080Ti GPU, it takes only about 1 hour for searching for denoising network on the BSD-500 dataset and 3.5 hours for searching for the super-resolution structure on the DIV2K dataset. Experiments show that the architectures found by HiNAS have fewer parameters and enjoy a faster inference speed, while achieving highly competitive performance compared with state-of-the-art methods. Code is available at: https://github.com/hkzhang91/HiNAS
Hierarchical Information Flow for Generalized Efficient Image Restoration
ETH Zürich（苏黎世联邦理工学院）；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 California, Merced（加州大学默塞德分校）
TPGDiff: Hierarchical Triple-Prior Guided Diffusion for Image Restoration
School of Computer Science, Northwestern Polytechnical University, Xi'an, China（西北工业大学计算机学院，西安，中国）；Shenzhen Research Institute of Northwestern Polytechnical University, Shenzhen, China（西北工业大学深圳研究院，深圳，中国）
Nanjing University of Science and Technology（南京理工大学）；Michigan State University（密歇根州立大学）
Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term dependency problem is rarely realized for these very deep models, which results in the prior states/layers having little influence on the subsequent ones. Motivated by the fact that human thoughts have persistency, we propose a very deep persistent memory network (MemNet) that introduces a memory block, consisting of a recursive unit and a gate unit, to explicitly mine persistent memory through an adaptive learning process. The re…
Northeastern University（东北大学）；University of Rochester（罗切斯特大学）；Rochester Institute of Technology（罗切斯特理工学院）；Huaqiao University（华侨大学）
Convolutional neural network has recently achieved great success for image restoration (IR) and also offered hierarchical features. However, most deep CNN based IR models do not make full use of the hierarchical features from the original low-quality images, thereby achieving relatively-low performance. In this paper, we propose a novel residual dense network (RDN) to address this problem in IR. We fully exploit the hierarchical features from all the convolutional layers. Specifically, we propose residual dense block (RDB) to extract abundant local features via densely connected convolutional …
AgileIR: Memory-Efficient Group Shifted Windows Attention for Agile Image Restoration
Faculty of Computer Science；Information Technology University of Malaya Kuala Lumpur, Malaysia；School of Intelligence Science；Technology University of Science；Faculty of Art；Design Fuzhou University of International Studies
In this paper, we propose a residual non-local attention network for high-quality image restoration. Without considering the uneven distribution of information in the corrupted images, previous methods are restricted by local convolutional operation and equal treatment of spatial- and channel-wise features. To address this issue, we design local and non-local attention blocks to extract features that capture the long-range dependencies between pixels and pay more attention to the challenging parts. Specifically, we design trunk branch and (non-)local mask branch in each (non-)local attention b…
Tremendous advances in image restoration tasks such as denoising and super-resolution have been achieved using neural networks. Such approaches generally employ very deep architectures, large number of parameters, large receptive fields and high nonlinear modeling capacity. In order to obtain efficient and fast image restoration networks one should improve upon the above mentioned requirements. In this paper we propose a novel activation function, the multi-bin trainable linear unit (MTLU), for increasing the nonlinear modeling capacity together with lighter and shallower networks. We validate…
Recently, deep convolutional neural network (CNN) have been widely used in image restoration and obtained great success. However, most of existing methods are limited to local receptive field and equal treatment of different types of information. Besides, existing methods always use a multi-supervised method to aggregate different feature maps, which can not effectively aggregate hierarchical feature information. To address these issues, we propose an attention cube network (A-CubeNet) for image restoration for more powerful feature expression and feature correlation learning. Specifically, we…
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…
Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；School of Life Sciences, Tsinghua University（清华大学生命科学学院）；Intelligent Science & Technology Academy of CASIC（中国科学院 CASIC 智能科学与技术学院）
SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder
Yau Mathematical Sciences Center, Tsinghua University（清华大学丘成桐数学科学中心）；Hisilicon（海思半导体）；Yanqi Lake Beijing Institute of Mathematical Sciences and Applications（雁栖湖北京数学科学与应用研究院）；State Key Laboratory of Membrane Biology, School of Life Sciences, Tsinghua University（清华大学生命科学学院膜生物学国家重点实验室）
City University of Hong Kong（香港城市大学）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）
Night imaging with modern smartphone cameras is troublesome due to low photon count and unavoidable noise in the imaging system. Directly adjusting exposure time and ISO ratings cannot obtain sharp and noise-free images at the same time in low-light conditions. Though many methods have been proposed to enhance noisy or blurry night images, their performances on real-world night photos are still unsatisfactory due to two main reasons: 1) Limited information in a single image and 2) Domain gap between synthetic training images and real-world photos (e.g., differences in blur area and resolution)…
Chiba University（千叶大学）；Kochi University（高知大学）；Tokyo University of Science（东京理科大学）
We propose a holographic image restoration method using an autoencoder, which is an artificial neural network. Because holographic reconstructed images are often contaminated by direct light, conjugate light, and speckle noise, the discrimination of reconstructed images may be difficult. In this paper, we demonstrate the restoration of reconstructed images from holograms that record page data in holographic memory and QR codes by using the proposed method.
DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration
School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；Shenzhen Research Institute of Northwestern Polytechnical University（西北工业大学深圳研究院）；State Key Laboratory of Internet of Things for Smart City, University of Macau（澳门大学智慧城市物联网国家重点实验室）
Inverse problem regularization with hierarchical variational autoencoders
Univ. Bordeaux（波尔多大学）；CNRS（法国国家科学研究中心）；Bordeaux INP（波尔多国立综合理工学院）；IMB（数学与计算机科学研究所）；Ubisoft La Forge（育碧拉福奇工作室）；Université Paris Cité（巴黎城市大学）；MAP5（数学与应用概率科学研究所）
Google Research（谷歌研究院）；Fondazione Human Technopole（人类技术城基金会）
Image denoising and artefact removal are complex inverse problems admitting multiple valid solutions. Unsupervised diversity restoration, that is, obtaining a diverse set of possible restorations given a corrupted image, is important for ambiguity removal in many applications such as microscopy where paired data for supervised training are often unobtainable. In real world applications, imaging noise and artefacts are typically hard to model, leading to unsatisfactory performance of existing unsupervised approaches. This work presents an interpretable approach for unsupervised and diverse imag…
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…
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）
Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task. To alleviate this problem, we raise the novel lifelong image restoration problem for blended distortions. We first design a base fork-join model in which multiple pre-trained expert models specializing in individual distortion removal task work cooperatively and adaptively to handle blended distortions. When the input is degraded by a new distortion, inspired by adult neurogenesis in human memory system, we develop a…
The ability to capture good quality images in the dark and near-zero lux conditions has been a long-standing pursuit of the computer vision community. The seminal work by Chen et al. [5] has especially caused renewed interest in this area, resulting in methods that build on top of their work in a bid to improve the reconstruction. However, for practical utility and deployment of low-light enhancement algorithms on edge devices such as embedded systems, surveillance cameras, autonomous robots and smartphones, the solution must respect additional constraints such as limited GPU memory and proces…
UniH$^3$: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration
School of Biological Science and Medical Engineering, Beihang University（北京航空航天大学生物科学与医学工程学院）；Department of Biomedical Engineering, Tsinghua University（清华大学生物医学工程系）
Couger Inc（库格公司）；Sethu Institute of Technology（塞图理工学院）；Thiagarajar college of Engineering（蒂亚加拉贾工程学院）
A moire pattern in the images is resulting from high frequency patterns captured by the image sensor (colour filter array) that appear after demosaicing. These Moire patterns would appear in natural images of scenes with high frequency content. The Moire pattern can also vary intensely due to a minimal change in the camera direction/positioning. Thus the Moire pattern depreciates the quality of photographs. An important issue in demoireing pattern is that the Moireing patterns have dynamic structure with varying colors and forms. These challenges makes the demoireing more difficult than many o…
National Chung Hsing University（国立中兴大学）；National Taichung University of Science and Technology（国立台中科技大学）
Image restoration is a low-level vision task which is to restore degraded images to noise-free images. With the success of deep neural networks, the convolutional neural networks surpass the traditional restoration methods and become the mainstream in the computer vision area. To advance the performanceof denoising algorithms, we propose a blind real image denoising network (SRMNet) by employing a hierarchical architecture improved from U-Net. Specifically, we use a selective kernel with residual block on the hierarchical structure called M-Net to enrich the multi-scale semantic information. F…
Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration
Biomedical Engineering Department, College of Future Technology, Peking University（北京大学未来技术学院生物医学工程系）；Institute of Medical Technology, Peking University Health Science Center（北京大学医学部医学技术研究所）；National Biomedical Imaging Center, Peking University（北京大学国家生物医学成像中心）
Hierarchical Semantic Compression for Consistent Image Semantic Restoration
School of Electronic and Information Engineering, Beihang University（北京航空航天大学电子信息工程学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Electronic and Information Engineering, University of Electronic Science and Technology of China（电子科技大学电子信息工程学院）
Harbin Institute of Technology（哈尔滨工业大学）；The Hong Kong Polytechnic University（香港理工大学）；Nanyang Technological University（南洋理工大学）；Peng Cheng Lab（鹏城实验室）
To improve the performance of blind face restoration, recent works mainly treat the two aspects, i.e., generic and specific restoration, separately. In particular, generic restoration attempts to restore the results through general facial structure prior, while on the one hand, cannot generalize to real-world degraded observations due to the limited capability of direct CNNs' mappings in learning blind restoration, and on the other hand, fails to exploit the identity-specific details. On the contrary, specific restoration aims to incorporate the identity features from the reference of the same…
National Laboratory of Pattern Recognition, CASIA（中国科学院自动化研究所模式识别国家重点实验室）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Blind face restoration (BFR) is a challenging problem because of the uncertainty of the degradation patterns. This paper proposes a Restoration with Memorized Modulation (RMM) framework for universal BFR in diverse degraded scenes and heterogeneous domains. We apply random noise as well as unsupervised wavelet memory to adaptively modulate the face-enhancement generator, considering attentional denormalization in both layer and instance levels. Specifically, in the training stage, the low-level spatial feature embedding, the wavelet memory embedding obtained by wavelet transformation of the hi…
We present Hierarchical Memory Matching Network (HMMN) for semi-supervised video object segmentation. Based on a recent memory-based method [33], we propose two advanced memory read modules that enable us to perform memory reading in multiple scales while exploiting temporal smoothness. We first propose a kernel guided memory matching module that replaces the non-local dense memory read, commonly adopted in previous memory-based methods. The module imposes the temporal smoothness constraint in the memory read, leading to accurate memory retrieval. More importantly, we introduce a hierarchical …
Recently, using diffusion models for zero-shot image restoration (IR) has become a new hot paradigm. This type of method only needs to use the pre-trained off-the-shelf diffusion models, without any finetuning, and can directly handle various IR tasks. The upper limit of the restoration performance depends on the pre-trained diffusion models, which are in rapid evolution. However, current methods only discuss how to deal with fixed-size images, but dealing with images of arbitrary sizes is very important for practical applications. This paper focuses on how to use those diffusion-based zero-sh…
Northwestern Polytechnical University（西北工业大学）；The University of Adelaide（阿德莱德大学）
Recently, neural architecture search (NAS) methods have attracted much attention and outperformed manually designed architectures on a few high-level vision tasks. In this paper, we propose HiNAS (Hierarchical NAS), an effort towards employing NAS to automatically design effective neural network architectures for image denoising. HiNAS adopts gradient based search strategies and employs operations with adaptive receptive field to build an flexible hierarchical search space. During the search stage, HiNAS shares cells across different feature levels to save memory and employ an early stopping s…
