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）
JiaKui Hu, Zhengjian Yao, Lujia Jin, Hangzhou He, Yanye Lu
Translation equivariance is a fundamental inductive bias in image restoration, ensuring that translated inputs produce translated outputs. Attention mechanisms in modern restoration transformers undermine this property, adversely impacting both training convergence and generalization. To alleviate this issue, we propose two key strategies for incorporating translation equivariance: slide indexing and component stacking. Slide indexing maintains operator responses at fixed positions, with sliding window attention being a notable example, while component stacking enables the arrangement of translation-equivariant operators in parallel or sequentially, thereby building complex architectures while preserving translation equivariance. However, these strategies still create a dilemma in model design between the high computational cost of self-attention and the fixed receptive field associated with sliding window attention. To address this, we develop an adaptive sliding indexing mechanism to efficiently select key-value pairs for each query, which are then concatenated in parallel with globally aggregated key-value pairs. The designed network, called the Translation Equivariance Adaptive Transformer (TEAFormer), is assessed across a variety of image restoration tasks. The results highlight its superiority in terms of effectiveness, training convergence, and generalization.
A Regularization-Guided Equivariant Approach for Image Restoration
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, China（西安交通大学数学与统计学学院）；Macau University of Science and Technology, Taipa, Macao（澳门科学技术大学）；Pengcheng Laboratory, Shenzhen, China（鹏城实验室）
CARL: A Framework for Equivariant Image Registration
UNC Chapel Hill（北卡罗来纳大学教堂山分校）；Université Gustave Eiffel（Gustave Eiffel 大学）；INRIA Paris（法国国家信息与自动化研究所巴黎分部）；University of Salzburg（萨尔茨堡大学）；Harvard Medical School（哈佛医学院）；UC San Diego（加州大学圣迭戈分校）
University of Illinois Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）
Image frames obtained in darkness are special. Just multiplying by a constant doesn't restore the image. Shot noise, quantization effects and camera non-linearities mean that colors and relative light levels are estimated poorly. Current methods learn a mapping using real dark-bright image pairs. These are very hard to capture. A recent paper has shown that simulated data pairs produce real improvements in restoration, likely because huge volumes of simulated data are easy to obtain. In this paper, we show that respecting equivariance -- the color of a restored pixel should be the same, howeve…
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…
Indian Institute of Technology Kharagpur（印度理工学院克勒格布尔分校）；Mathworks（Mathworks公司）
Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource constrained platform like a mobile phone. In this paper, we propose several lightweight low-level modules which can be used to create a computationally low cost variant of a given baseline model. Recent works for efficient neural networks design have mainly focused on classification. However, low-level image processing falls under the image-to-image' translation …
UvA-Bosch Delta Lab（阿姆斯特丹大学-博世Delta实验室）；University of Amsterdam（阿姆斯特丹大学）
Siamese trackers turn tracking into similarity estimation between a template and the candidate regions in the frame. Mathematically, one of the key ingredients of success of the similarity function is translation equivariance. Non-translation-equivariant architectures induce a positional bias during training, so the location of the target will be hard to recover from the feature space. In real life scenarios, objects undergoe various transformations other than translation, such as rotation or scaling. Unless the model has an internal mechanism to handle them, the similarity may degrade. In thi…
A Generative Data Framework with Authentic Supervision for Underwater Image Restoration and Enhancement
Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）；Department of Automation, Shanghai Jiao Tong University（自动化系，上海交通大学）；School of Artificial Intelligence, Optics and ElectroNics (iOPEN), Northwestern Polytechnical University（人工智能、光学与电子学学院（iOPEN），西北工业大学）；Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences（西安光学精密机械研究所，中国科学院）
With the recent increase in intelligent CCTVs for visual surveillance, a new image degradation that integrates resolution conversion and synthetic rain models is required. For example, in heavy rain, face images captured by CCTV from a distance have significant deterioration in both visibility and resolution. Unlike traditional image degradation models (IDM), such as rain removal and superresolution, this study addresses a new IDM referred to as a scale-aware heavy rain model and proposes a method for restoring high-resolution face images (HR-FIs) from low-resolution heavy rain face images (LR…
Translating or rotating an input image should not affect the results of many computer vision tasks. Convolutional neural networks (CNNs) are already translation equivariant: input image translations produce proportionate feature map translations. This is not the case for rotations. Global rotation equivariance is typically sought through data augmentation, but patch-wise equivariance is more difficult. We present Harmonic Networks or H-Nets, a CNN exhibiting equivariance to patch-wise translation and 360-rotation. We achieve this by replacing regular CNN filters with circular harmonics, return…
While Transformer architectures have show remarkable success, they are bound to the computation of all pairwise interactions of input element and thus suffer from limited scalability. Recent work has been successful by avoiding the computation of the complete attention matrix, yet leads to problems down the line. The absence of an explicit attention matrix makes the inclusion of inductive biases relying on relative interactions between elements more challenging. An extremely powerful inductive bias is translational equivariance, which has been conjectured to be responsible for much of the succ…
Chalmers University of Technology（查尔姆斯理工大学）；Umeå University（于默奥大学）
We characterize the class of image plane transformations which realize rigid camera motions and call these transformations `rigidity preserving'. In particular, 2D translations of pinhole images are not rigidity preserving. Hence, when using CNNs for 3D inference tasks, it can be beneficial to modify the inductive bias from equivariance towards translations to equivariance towards rigidity preserving transformations. We investigate how equivariance with respect to rigidity preserving transformations can be approximated in CNNs, and test our ideas on both 6D object pose estimation and visual lo…
University of Washington（华盛顿大学）；Purdue University（普渡大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Incorporating group symmetry directly into the learning process has proved to be an effective guideline for model design. By producing features that are guaranteed to transform covariantly to the group actions on the inputs, group-equivariant convolutional neural networks (G-CNNs) achieve significantly improved generalization performance in learning tasks with intrinsic symmetry. General theory and practical implementation of G-CNNs have been studied for planar images under either rotation or scaling transformation, but only individually. We present, in this paper, a roto-scale-translation equ…
In this work we investigate how to achieve equivariance to input transformations in deep networks, purely from data, without being given a model of those transformations. Convolutional Neural Networks (CNNs), for example, are equivariant to image translation, a transformation that can be easily modelled (by shifting the pixels vertically or horizontally). Other transformations, such as out-of-plane rotations, do not admit a simple analytic model. We propose an auto-encoder architecture whose embedding obeys an arbitrary set of equivariance relations simultaneously, such as translation, rotatio…
Computer Science Department, University College London（伦敦大学学院计算机科学系）
3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would preserve a meaningful representation of the voxelized object, while explaining the pose-difference between the two inputs. An equivariant representation vector has two components: the invariant identity part, and a discernable encoding of the transformation. Models that can't explain pose-differences r…
GRASP Laboratory, University of Pennsylvania（宾夕法尼亚大学GRASP实验室）
Convolutional neural networks (CNNs) are inherently equivariant to translation. Efforts to embed other forms of equivariance have concentrated solely on rotation. We expand the notion of equivariance in CNNs through the Polar Transformer Network (PTN). PTN combines ideas from the Spatial Transformer Network (STN) and canonical coordinate representations. The result is a network invariant to translation and equivariant to both rotation and scale. PTN is trained end-to-end and composed of three distinct stages: a polar origin predictor, the newly introduced polar transformer module and a classif…
Robustness to small image translations is a highly desirable property for object detectors. However, recent works have shown that CNN-based classifiers are not shift invariant. It is unclear to what extent this could impact object detection, mainly because of the architectural differences between the two and the dimensionality of the prediction space of modern detectors. To assess shift equivariance of object detection models end-to-end, in this paper we propose an evaluation metric, built upon a greedy search of the lower and upper bounds of the mean average precision on a shifted image set. …
Harvard University（哈佛大学）；Harvard-Smithsonian Center for Astrophysics（哈佛-史密森天体物理中心）
Wavelet scattering networks, which are convolutional neural networks (CNNs) with fixed filters and weights, are promising tools for image analysis. Imposing symmetry on image statistics can improve human interpretability, aid in generalization, and provide dimension reduction. In this work, we introduce a fast-to-compute, translationally invariant and rotationally equivariant wavelet scattering network (EqWS) and filter bank of wavelets (triglets). We demonstrate the interpretability and quantify the invariance/equivariance of the coefficients, briefly commenting on difficulties with implement…
Convolutional neural networks (CNN) are now being widely used for classifying and detecting pulmonary abnormalities in chest radiographs. Two complementary generalization properties of CNNs, translation invariance and equivariance, are particularly useful in detecting manifested abnormalities associated with pulmonary disease, regardless of their spatial locations within the image. However, these properties also come with the loss of exact spatial information and global relative positions of abnormalities detected in local regions. Global relative positions of such abnormalities may help disti…
City University of Hong Kong（香港城市大学）；Microsoft Research（微软研究院）；Microsoft Cloud+AI（微软云与人工智能）；University of Science and Technology of China（中国科学技术大学）
We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize. Therefore, we propose a novel triplet domain translation network by leveraging real photos along with massive synthetic image pairs. Specifically, we train two variational autoencoders (VAEs) to respectively transform old photos and clean photos into two latent space…
Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting symmetries (e.g. scalings, rotations, translations). The method of moving frames is classical for deriving operators invariant to the action of a Lie group in a manifold.Recently, a rotation and translation equivariant neural network for image data was proposed based on the moving frames approach. In this paper we significantly improve that approach by reducing the computation of moving frames to only one, at the in…
Convolutional networks are successful due to their equivariance/invariance under translations. However, rotatable data such as images, volumes, shapes, or point clouds require processing with equivariance/invariance under rotations in cases where the rotational orientation of the coordinate system does not affect the meaning of the data (e.g. object classification). On the other hand, estimation/processing of rotations is necessary in cases where rotations are important (e.g. motion estimation). There has been recent progress in methods and theory in all these regards. Here we provide an overv…
Npix2Cpix: A GAN-Based Image-to-Image Translation Network With Retrieval- Classification Integration for Watermark Retrieval From Historical Document Images
BRAC University（BRAC大学）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
Rotation-invariance is a desired property of machine-learning models for medical image analysis and in particular for computational pathology applications. We propose a framework to encode the geometric structure of the special Euclidean motion group SE(2) in convolutional networks to yield translation and rotation equivariance via the introduction of SE(2)-group convolution layers. This structure enables models to learn feature representations with a discretized orientation dimension that guarantees that their outputs are invariant under a discrete set of rotations. Conventional approaches fo…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
Image-to-image translation (I2I) aims to transfer images from a source domain to a target domain while preserving the content representations. I2I has drawn increasing attention and made tremendous progress in recent years because of its wide range of applications in many computer vision and image processing problems, such as image synthesis, segmentation, style transfer, restoration, and pose estimation. In this paper, we provide an overview of the I2I works developed in recent years. We will analyze the key techniques of the existing I2I works and clarify the main progress the community has …
DATA61-CSIRO（澳大利亚联邦科学与工业研究组织数据61）；Australian National University（澳大利亚国立大学）
Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world. This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on the unsupervised image-to-image translation framework. We design our method by leveraging from contrastive learning and generative adversarial networks to maximize mutual information between raw and restored images. Additionally, we release a large-scale real underwater image dataset to support both paired and unpaired training modules. Extensive experiments w…
Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Friedrich-Alexander University Erlangen-Nuremberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）
This is an exploratory study that discovers the current image quantization (vector quantization) do not satisfy translation equivariance in the quantized space due to aliasing. Instead of focusing on anti-aliasing, we propose a simple yet effective way to achieve translation-equivariant image quantization by enforcing orthogonality among the codebook embeddings. To explore the advantages of translation-equivariant image quantization, we conduct three proof-of-concept experiments with a carefully controlled dataset: (1) text-to-image generation, where the quantized image indices are the target …
Recovery of true color from underwater images is an ill-posed problem. This is because the wide-band attenuation coefficients for the RGB color channels depend on object range, reflectance, etc. which are difficult to model. Also, there is backscattering due to suspended particles in water. Thus, most existing deep-learning based color restoration methods, which are trained on synthetic underwater datasets, do not perform well on real underwater data. This can be attributed to the fact that synthetic data cannot accurately represent real conditions. To address this issue, we use an image to im…
Adaptive Domain Shift in Diffusion Models for Cross-Modality Image Translation
Laplace Lab at University of Tennessee（田纳西大学Laplace实验室）；University of California Riverside（加州大学河滨分校）；University of Tennessee at Chattanooga（田纳西大学查塔努加分校）
Commonwealth Scientific and Industrial Research Organisation (CSIRO)（澳大利亚联邦科学与工业研究组织）；Australian National University（澳大利亚国立大学）
Underwater image restoration is of significant importance in unveiling the underwater world. Numerous techniques and algorithms have been developed in the past decades. However, due to fundamental difficulties associated with imaging/sensing, lighting, and refractive geometric distortions, in capturing clear underwater images, no comprehensive evaluations have been conducted of underwater image restoration. To address this gap, we have constructed a large-scale real underwater image dataset, dubbed `HICRD' (Heron Island Coral Reef Dataset), for the purpose of benchmarking existing methods and …
