Establishing correspondences between 3D shapes is a fundamental task in 3D Computer Vision, typically addressed by matching local descriptors. Recently, a few attempts at applying the deep learning paradigm to the task have shown promising results. Yet, the only explored way to learn rotation invariant descriptors has been to feed neural networks with highly engineered and invariant representations provided by existing hand-crafted descriptors, a path that goes in the opposite direction of end-to-end learning from raw data so successfully deployed for 2D images. In this paper, we explore the benefits of taking a step back in the direction of end-to-end learning of 3D descriptors by disentangling the creation of a robust and distinctive rotation equivariant representation, which can be learned from unoriented input data, and the definition of a good canonical orientation, required only at test time to obtain an invariant descriptor. To this end, we leverage two recent innovations: spherical convolutional neural networks to learn an equivariant descriptor and plane folding decoders to learn without supervision. The effectiveness of the proposed approach is experimentally validated by outperforming hand-crafted and learned descriptors on a standard benchmark.
Wuhan University（武汉大学）；The University of Hong Kong（香港大学）；Texas A&M University（得克萨斯农工大学）
In this paper, we propose a novel local descriptor-based framework, called You Only Hypothesize Once (YOHO), for the registration of two unaligned point clouds. In contrast to most existing local descriptors which rely on a fragile local reference frame to gain rotation invariance, the proposed descriptor achieves the rotation invariance by recent technologies of group equivariant feature learning, which brings more robustness to point density and noise. Meanwhile, the descriptor in YOHO also has a rotation equivariant part, which enables us to estimate the registration from just one correspon…
Pohang University of Science and Technology (POSTECH)（浦项科技大学）
Extracting discriminative local features that are invariant to imaging variations is an integral part of establishing correspondences between images. In this work, we introduce a self-supervised learning framework to extract discriminative rotation-invariant descriptors using group-equivariant CNNs. Thanks to employing group-equivariant CNNs, our method effectively learns to obtain rotation-equivariant features and their orientations explicitly, without having to perform sophisticated data augmentations. The resultant features and their orientations are further processed by group aligning, a n…
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background. Our method relies on moving objects being equivariant with respect to their transformation across frames and the background being constant. After training, we can manipulate and render the scenes in real time to create unseen combinations of objects, transformations, and backgrounds. We show results on moving MNIST with backgrounds.
Standard losses for training deep segmentation networks could be seen as individual classifications of pixels, instead of supervising the global shape of the predicted segmentations. While effective, they require exact knowledge of the label of each pixel in an image. This study investigates how effective global geometric shape descriptors could be, when used on their own as segmentation losses for training deep networks. Not only interesting theoretically, there exist deeper motivations to posing segmentation problems as a reconstruction of shape descriptors: Annotations to obtain approximati…
University of Pennsylvania（宾夕法尼亚大学）；Stanford University（斯坦福大学）
We introduce Equivariant Neural Field Expectation Maximization (EFEM), a simple, effective, and robust geometric algorithm that can segment objects in 3D scenes without annotations or training on scenes. We achieve such unsupervised segmentation by exploiting single object shape priors. We make two novel steps in that direction. First, we introduce equivariant shape representations to this problem to eliminate the complexity induced by the variation in object configuration. Second, we propose a novel EM algorithm that can iteratively refine segmentation masks using the equivariant shape prior.…
Georgia Institute of Technology（佐治亚理工学院）；Microsoft Research（微软研究院）
Image alignment tasks require accurate pixel correspondences, which are usually recovered by matching local feature descriptors. Such descriptors are often derived using supervised learning on existing datasets with ground truth correspondences. However, the cost of creating such datasets is usually prohibitive. In this paper, we propose a new approach to align two images related by an unknown 2D homography where the local descriptor is learned from scratch from the images and the homography is estimated simultaneously. Our key insight is that a siamese convolutional neural network can be trai…
Massachusetts Institute of Technology（麻省理工学院）；Google Research（谷歌研究院）；University of Toronto（多伦多大学）
We present Neural Descriptor Fields (NDFs), an object representation that encodes both points and relative poses between an object and a target (such as a robot gripper or a rack used for hanging) via category-level descriptors. We employ this representation for object manipulation, where given a task demonstration, we want to repeat the same task on a new object instance from the same category. We propose to achieve this objective by searching (via optimization) for the pose whose descriptor matches that observed in the demonstration. NDFs are conveniently trained in a self-supervised fashion…
University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due to the gap between full and weak supervisions. In this paper, we propose a self-supervised equivariant attention mechanism (SEAM) to discover additional supervision and narrow the gap. Our method is based on the observation that equivariance is an implicit constraint in fully supervised semantic segmentation, whose pixel-level labels take the same spatial tr…
Unitary；VGG, University of Oxford（牛津大学VGG）；University of Edinburgh（爱丁堡大学）
Equivariance to random image transformations is an effective method to learn landmarks of object categories, such as the eyes and the nose in faces, without manual supervision. However, this method does not explicitly guarantee that the learned landmarks are consistent with changes between different instances of the same object, such as different facial identities. In this paper, we develop a new perspective on the equivariance approach by noting that dense landmark detectors can be interpreted as local image descriptors equipped with invariance to intra-category variations. We then propose a …
Thin, reflective objects such as forks and whisks are common in our daily lives, but they are particularly challenging for robot perception because it is hard to reconstruct them using commodity RGB-D cameras or multi-view stereo techniques. While traditional pipelines struggle with objects like these, Neural Radiance Fields (NeRFs) have recently been shown to be remarkably effective for performing view synthesis on objects with thin structures or reflective materials. In this paper we explore the use of NeRF as a new source of supervision for robust robot vision systems. In particular, we dem…
Inria Grenoble Rhone-Alpes（法国国家信息与自动化研究所格勒诺布尔-罗讷阿尔卑斯分院）；Laboratoire Jean Kuntzmann（让·孔茨曼实验室）；CNRS（法国国家科学研究中心）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）
Convolutional neural networks (CNNs) have recently received a lot of attention due to their ability to model local stationary structures in natural images in a multi-scale fashion, when learning all model parameters with supervision. While excellent performance was achieved for image classification when large amounts of labeled visual data are available, their success for un-supervised tasks such as image retrieval has been moderate so far. Our paper focuses on this latter setting and explores several methods for learning patch descriptors without supervision with application to matching and i…
Improbable AI Lab（Improbable人工智能实验室）；CSAIL（计算机科学与人工智能实验室）；Massachusetts Institute of Technology（麻省理工学院）
We present a method for performing tasks involving spatial relations between novel object instances initialized in arbitrary poses directly from point cloud observations. Our framework provides a scalable way for specifying new tasks using only 5-10 demonstrations. Object rearrangement is formalized as the question of finding actions that configure task-relevant parts of the object in a desired alignment. This formalism is implemented in three steps: assigning a consistent local coordinate frame to the task-relevant object parts, determining the location and orientation of this coordinate fram…
CTU in Prague（布拉格捷克理工大学）；Facebook AI Research（脸书人工智能研究院）
We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients. It combines two parametrizations of gradient position and direction, each parametrization provides robustness to a different type of patch mis-registration: polar parametrization for noise in the patch dominant orientation detection, Cartesian for imprecise location of the feature point. Combined with whitening of the descriptor space, that is learned with or without supervision, the performance is significantly improved. We analyze the effect of the whitening on patch similarity and demo…
VNI-Net: Vector Neurons-based Rotation-Invariant Descriptor for LiDAR Place Recognition
Department of Computer Science and Technology, School of Electronics and Information Engineering, Tongji University（同济大学电子信息工程学院计算机科学与技术系）；MOE Key Lab of Embedded System and Service Computing, Tongji University（同济大学嵌入式系统与服务计算教育部重点实验室）；Institute of Intelligent Vehicles, Tongji University（同济大学智能汽车研究所）
University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Weakly supervised semantic segmentation has attracted much research interest in recent years considering its advantage of low labeling cost. Most of the advanced algorithms follow the design principle that expands and constrains the seed regions from class activation maps (CAM). As well-known, conventional CAM tends to be incomplete or over-activated due to weak supervision. Fortunately, we find that semantic segmentation has a characteristic of spatial transformation equivariance, which can form a few self-supervisions to help weakly supervised learning. This work mainly explores the advantag…
Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration
Faculty of Electrical Engineering, KU Leuven（KU Leuven 电气工程学院）；Spatial Intelligence Group, The Hong Kong Polytechnic University（香港理工大学 空间智能组）；Faculty of Engineering and IT, The University of Melbourne（墨尔本大学 工程与信息技术学院）；IoTUS Lab, Queen Mary University of London（伦敦大学玛丽女王学院 IoTUS实验室）
MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering
School of Computer Science and Technology, Tongji University, Shanghai, China（计算机科学与技术学院，同济大学，上海，中国）；MOE Key Lab of Embedded System and Service Computing, Tongji University, Shanghai, China（教育部嵌入式系统与服务计算重点实验室，同济大学，上海，中国）；Shanghai Research Institute for Intelligent Autonomous System, Tongji University, Shanghai, China（上海智能自主系统研究院，同济大学，上海，中国）；School of Surveying and Geo-Informatics, Tongji University, Shanghai, China（测绘地理信息学院，同济大学，上海，中国）
Thales LAS France（泰雷兹LAS法国公司）；LIGM (UMR 8049), Ecole des Ponts, Univ. Gustave Eiffel, CNRS, Marne-la-Vallée, France（LIGM（UMR 8049），巴黎高科路桥学校，古斯塔夫·埃菲尔大学，法国国家科学研究中心，马恩拉瓦莱，法国）
We tackle the problem of finding accurate and robust keypoint correspondences between images. We propose a learning-based approach to guide local feature matches via a learned approximate image matching. Our approach can boost the results of SIFT to a level similar to state-of-the-art deep descriptors, such as Superpoint, ContextDesc, or D2-Net and can improve performance for these descriptors. We introduce and study different levels of supervision to learn coarse correspondences. In particular, we show that weak supervision from epipolar geometry leads to performances higher than the stronger…
Several popular approaches to 3D vision tasks process multiple views of the input independently with deep neural networks pre-trained on natural images, achieving view permutation invariance through a single round of pooling over all views. We argue that this operation discards important information and leads to subpar global descriptors. In this paper, we propose a group convolutional approach to multiple view aggregation where convolutions are performed over a discrete subgroup of the rotation group, enabling, thus, joint reasoning over all views in an equivariant (instead of invariant) fash…
University of Southern California（南加州大学）；USC Institute for Creative Technologies（南加州大学创意技术研究所）；Tencent Game AI Research Center（腾讯游戏AI研究中心）；Pinscreen
Features that are equivariant to a larger group of symmetries have been shown to be more discriminative and powerful in recent studies. However, higher-order equivariant features often come with an exponentially-growing computational cost. Furthermore, it remains relatively less explored how rotation-equivariant features can be leveraged to tackle 3D shape alignment tasks. While many past approaches have been based on either non-equivariant or invariant descriptors to align 3D shapes, we argue that such tasks may benefit greatly from an equivariant framework. In this paper, we propose an effec…
One of the key challenges of visual perception is to extract abstract models of 3D objects and object categories from visual measurements, which are affected by complex nuisance factors such as viewpoint, occlusion, motion, and deformations. Starting from the recent idea of viewpoint factorization, we propose a new approach that, given a large number of images of an object and no other supervision, can extract a dense object-centric coordinate frame. This coordinate frame is invariant to deformations of the images and comes with a dense equivariant labelling neural network that can map image p…
Latest results indicate that features learned via convolutional neural networks outperform previous descriptors on classification tasks by a large margin. It has been shown that these networks still work well when they are applied to datasets or recognition tasks different from those they were trained on. However, descriptors like SIFT are not only used in recognition but also for many correspondence problems that rely on descriptor matching. In this paper we compare features from various layers of convolutional neural nets to standard SIFT descriptors. We consider a network that was trained o…
How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground Localization
The Hong Kong Polytechnic University（香港理工大学）；Southern University of Science and Technology（南方科技大学）；Wuhan University（武汉大学）；The Chinese University of Hong Kong（香港中文大学）；Huawei Technologies Co., Ltd（华为技术有限公司）
SHReg: Strictly Rotation-Equivariant Point Cloud Registration via Spherical Harmonics
College of Mathematics and Systems Science, Shandong University of Science and Technology（山东科技大学数学与系统科学学院）；School of Artificial Intelligence, Shandong Women’s University（山东女子学院人工智能学院）
University of Pennsylvania（宾夕法尼亚大学）；Google Research（谷歌研究院）
Spherical convolutional networks have been introduced recently as tools to learn powerful feature representations of 3D shapes. Spherical CNNs are equivariant to 3D rotations making them ideally suited to applications where 3D data may be observed in arbitrary orientations. In this paper we learn 2D image embeddings with a similar equivariant structure: embedding the image of a 3D object should commute with rotations of the object. We introduce a cross-domain embedding from 2D images into a spherical CNN latent space. This embedding encodes images with 3D shape properties and is equivariant to…
Automatic lesion segmentation in dermoscopy images is an essential step for computer-aided diagnosis of melanoma. The dermoscopy images exhibits rotational and reflectional symmetry, however, this geometric property has not been encoded in the state-of-the-art convolutional neural networks based skin lesion segmentation methods. In this paper, we present a deeply supervised rotation equivariant network for skin lesion segmentation by extending the recent group rotation equivariant network~\cite{cohen2016group}. Specifically, we propose the G-upsampling and G-projection operations to adapt the …
Objects in aerial images have greater variations in scale and orientation than in typical images, so detection is more difficult. Convolutional neural networks use a variety of frequency- and orientation-specific kernels to identify objects subject to different transformations; these require many parameters. Sampling equivariant networks can adjust sampling from input feature maps according to the transformation of the object, allowing a kernel to extract features of an object under different transformations. Doing so requires fewer parameters, and makes the network more suitable for represent…
Unsupervised feature learning has shown impressive results for a wide range of input modalities, in particular for object classification tasks in computer vision. Using a large amount of unlabeled data, unsupervised feature learning methods are utilized to construct high-level representations that are discriminative enough for subsequently trained supervised classification algorithms. However, it has never been \emph{quantitatively} investigated yet how well unsupervised learning methods can find \emph{low-level representations} for image patches without any additional supervision. In this pap…
NEC Laboratories America, Inc.（美国NEC实验室公司）；University of California, San Diego（加州大学圣迭戈分校）；Google Cloud AI（谷歌云人工智能）；Microsoft Hololens（微软HoloLens）
Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors that outperform hand-crafted descriptors on many problems. We demonstrate that commonly used metric learning approaches do not optimally leverage the feature hierarchies learned in a Convolutional Neural Network (CNN), especially when applied to the task of geometric feature matching. While a metric loss applied to the deepest layer of a CNN, is often expected to yield ideal features irrespective of the task, in fact …
University of Oxford（牛津大学）；NAVER LABS Europe（欧洲NAVER实验室）
Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks. While self-supervision has usually been considered for tasks such as image classification, in this paper we aim at extending it to geometry-oriented tasks such as semantic matching and part detection. We do so by building on several recent ideas in unsupervised landmark detection. Our approach learns dense distinctive visual descriptors from an unlabelled dataset of images using synthetic image transformations. It does so by means of a robust probabilistic formulation that ca…
Sun Yat-sen University（中山大学）；University of Oxford（牛津大学）；The Hong Kong Polytechnic University（香港理工大学）；National University of Defense Technology（国防科技大学）
Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction. Existing learning-based local descriptors are either sensitive to rotation transformations, or rely on classical handcrafted features which are neither general nor representative. In this paper, we introduce a new, yet conceptually simple, neural architecture, termed SpinNet, to extract local features which are rotationally invariant whilst sufficiently informative to enable accurate registration. A Spatial Point Transformer is first introduced to map the input local …
We propose a framework for learning neural scene representations directly from images, without 3D supervision. Our key insight is that 3D structure can be imposed by ensuring that the learned representation transforms like a real 3D scene. Specifically, we introduce a loss which enforces equivariance of the scene representation with respect to 3D transformations. Our formulation allows us to infer and render scenes in real time while achieving comparable results to models requiring minutes for inference. In addition, we introduce two challenging new datasets for scene representation and neural…
Technische Universität München（慕尼黑工业大学）；Siemens AG（西门子股份公司）；National University of Defense Technology（国防科技大学）
We present PPF-FoldNet for unsupervised learning of 3D local descriptors on pure point cloud geometry. Based on the folding-based auto-encoding of well known point pair features, PPF-FoldNet offers many desirable properties: it necessitates neither supervision, nor a sensitive local reference frame, benefits from point-set sparsity, is end-to-end, fast, and can extract powerful rotation invariant descriptors. Thanks to a novel feature visualization, its evolution can be monitored to provide interpretable insights. Our extensive experiments demonstrate that despite having six degree-of-freedom …
Multi-view stereo (MVS) is the golden mean between the accuracy of active depth sensing and the practicality of monocular depth estimation. Cost volume based approaches employing 3D convolutional neural networks (CNNs) have considerably improved the accuracy of MVS systems. However, this accuracy comes at a high computational cost which impedes practical adoption. Distinct from cost volume approaches, we propose an efficient depth estimation approach by first (a) detecting and evaluating descriptors for interest points, then (b) learning to match and triangulate a small set of interest points,…
School of Natural and Computing Sciences, University of Aberdeen, UK（自然与计算科学学院，阿伯丁大学）；Interdisciplinary Institute, University of Aberdeen, UK（跨学科研究院，阿伯丁大学）；School of Computer Science, University of Lincoln, UK（计算机科学学院，林肯大学）
In this paper, we explore how three related tasks, namely keypoint detection, description, and image retrieval can be jointly tackled using a single unified framework, which is trained without the need of training data with point to point correspondences. By leveraging diverse information from sequential layers of a standard ResNet-based architecture, we are able to extract keypoints and descriptors that encode local information using generic techniques such as local activation norms, channel grouping and dropping, and self-distillation. Subsequently, global information for image retrieval is …
University of Padova（帕多瓦大学）；Stanford University（斯坦福大学）；TU Munich（慕尼黑工业大学）；TU Dortmund（多特蒙德工业大学）；Google（谷歌）
We present a 3D capsule module for processing point clouds that is equivariant to 3D rotations and translations, as well as invariant to permutations of the input points. The operator receives a sparse set of local reference frames, computed from an input point cloud and establishes end-to-end transformation equivariance through a novel dynamic routing procedure on quaternions. Further, we theoretically connect dynamic routing between capsules to the well-known Weiszfeld algorithm, a scheme for solving \emph{iterative re-weighted least squares} (IRLS) problems with provable convergence propert…
Self-supervised learning of Split Invariant Equivariant representations
Meta AI - FAIR（Meta人工智能基础研究实验室）；Univ Gustave Eiffel（古斯塔夫·埃菲尔大学）；CNRS（法国国家科学研究中心）；Courant Institute, New York University（纽约大学柯朗研究所）；Center for Data Science, New York University（纽约大学数据科学中心）
Simons Machine Learning Center（西蒙斯机器学习中心）；New York Structural Biology Center（纽约结构生物学中心）
In many imaging modalities, objects of interest can occur in a variety of locations and poses (i.e. are subject to translations and rotations in 2d or 3d), but the location and pose of an object does not change its semantics (i.e. the object's essence). That is, the specific location and rotation of an airplane in satellite imagery, or the 3d rotation of a chair in a natural image, or the rotation of a particle in a cryo-electron micrograph, do not change the intrinsic nature of those objects. Here, we consider the problem of learning semantic representations of objects that are invariant to p…
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…
