Motivated by the intuition that one can transform two aligned point clouds to each other more easily and meaningfully than a misaligned pair, we propose CorrNet3D -- the first unsupervised and end-to-end deep learning-based framework -- to drive the learning of dense correspondence between 3D shapes by means of deformation-like reconstruction to overcome the need for annotated data. Specifically, CorrNet3D consists of a deep feature embedding module and two novel modules called correspondence indicator and symmetric deformer. Feeding a pair of raw point clouds, our model first learns the pointwise features and passes them into the indicator to generate a learnable correspondence matrix used to permute the input pair. The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence. The extensive experiments on both synthetic and real-world datasets of rigid and non-rigid 3D shapes show our CorrNet3D outperforms state-of-the-art methods to a large extent, including those taking meshes as input. CorrNet3D is a flexible framework in that it can be easily adapted to supervised learning if annotated data are available. The source code and pre-trained model will be available at https://github.com/ZENGYIMING-EAMON/CorrNet3D.git.
Northwestern Polytechnical University（西北工业大学）；Baidu Research（百度研究院）；National Engineering Laboratory of Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）
3D point cloud registration in remote sensing field has been greatly advanced by deep learning based methods, where the rigid transformation is either directly regressed from the two point clouds (correspondences-free approaches) or computed from the learned correspondences (correspondences-based approaches). Existing correspondences-free methods generally learn the holistic representation of the entire point cloud, which is fragile for partial and noisy point clouds. In this paper, we propose a correspondences-free unsupervised point cloud registration (UPCR) method from the representation se…
We present Neural Correspondence Prior (NCP), a new paradigm for computing correspondences between 3D shapes. Our approach is fully unsupervised and can lead to high-quality correspondences even in challenging cases such as sparse point clouds or non-isometric meshes, where current methods fail. Our first key observation is that, in line with neural priors observed in other domains, recent network architectures on 3D data, even without training, tend to produce pointwise features that induce plausible maps between rigid or non-rigid shapes. Secondly, we show that given a noisy map as input, tr…
University of Florida（佛罗里达大学）；National Renewable Energy Lab（美国国家可再生能源实验室）
We present a new approach to unsupervised shape correspondence learning between pairs of point clouds. We make the first attempt to adapt the classical locally linear embedding algorithm (LLE) -- originally designed for nonlinear dimensionality reduction -- for shape correspondence. The key idea is to find dense correspondences between shapes by first obtaining high-dimensional neighborhood-preserving embeddings of low-dimensional point clouds and subsequently aligning the source and target embeddings using locally linear transformations. We demonstrate that learning the embedding using a new …
We present a new method for real-time non-rigid dense correspondence between point clouds based on structured shape construction. Our method, termed Deep Point Correspondence (DPC), requires a fraction of the training data compared to previous techniques and presents better generalization capabilities. Until now, two main approaches have been suggested for the dense correspondence problem. The first is a spectral-based approach that obtains great results on synthetic datasets but requires mesh connectivity of the shapes and long inference processing time while being unstable in real-world scen…
We present a new paradigm for rigid alignment between point clouds based on learnable weighted consensus which is robust to noise as well as the full spectrum of the rotation group. Current models, learnable or axiomatic, work well for constrained orientations and limited noise levels, usually by an end-to-end learner or an iterative scheme. However, real-world tasks require us to deal with large rotations as well as outliers and all known models fail to deliver. Here we present a different direction. We claim that we can align point clouds out of sampled matched points according to confidence…
City University of Hong Kong（香港城市大学）；Xi’an Jiaotong University（西安交通大学）
We present neural radiance fields (NeRF) with templates, dubbed Template-NeRF, for modeling appearance and geometry and generating dense shape correspondences simultaneously among objects of the same category from only multi-view posed images, without the need of either 3D supervision or ground-truth correspondence knowledge. The learned dense correspondences can be readily used for various image-based tasks such as keypoint detection, part segmentation, and texture transfer that previously require specific model designs. Our method can also accommodate annotation transfer in a one or few-shot…
Technical University of Munich（慕尼黑工业大学）；University of Toulouse（图卢兹大学）；Mikros Image
We introduce a variational method for multi-view shape-from-shading under natural illumination. The key idea is to couple PDE-based solutions for single-image based shape-from-shading problems across multiple images and multiple color channels by means of a variational formulation. Rather than alternatingly solving the individual SFS problems and optimizing the consistency across images and channels which is known to lead to suboptimal results, we propose an efficient solution of the coupled problem by means of an ADMM algorithm. In numerous experiments on both simulated and real imagery, we d…
Sichuan University（四川大学）；The University of Western Australia（西澳大学）；Central South University（中南大学）；Monash University（莫纳什大学）
Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real scenes. However, large disparities between existing synthetic datasets and real scenes lead to poor model transfer. We make two major contributions to address that. First, we develop a point cloud collector and scene flow annotator for GTA-V engine to automatically obtain diverse realistic training samples without human intervention. With that, we develop a larg…
SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising
National Key Laboratory of Microwave Imaging, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China（微波成像国家重点实验室，航天信息研究所，中国科学院，北京，中国）；School of Computing, National University of Singapore, Singapore（计算学院，新加坡国立大学，新加坡）
Aalto University（阿尔托大学）；University of Oulu（奥卢大学）；ETH Zürich（苏黎世联邦理工学院）；Microsoft（微软）；Tampere University of Technology（坦佩雷理工大学）
This paper addresses the challenge of dense pixel correspondence estimation between two images. This problem is closely related to optical flow estimation task where ConvNets (CNNs) have recently achieved significant progress. While optical flow methods produce very accurate results for the small pixel translation and limited appearance variation scenarios, they hardly deal with the strong geometric transformations that we consider in this work. In this paper, we propose a coarse-to-fine CNN-based framework that can leverage the advantages of optical flow approaches and extend them to the case…
National Tsing-Hua University（国立清华大学）；University of California, Merced（加州大学默塞德分校）；NVIDIA（英伟达）
We propose a canonical point autoencoder (CPAE) that predicts dense correspondences between 3D shapes of the same category. The autoencoder performs two key functions: (a) encoding an arbitrarily ordered point cloud to a canonical primitive, e.g., a sphere, and (b) decoding the primitive back to the original input instance shape. As being placed in the bottleneck, this primitive plays a key role to map all the unordered point clouds on the canonical surface and to be reconstructed in an ordered fashion. Once trained, points from different shape instances that are mapped to the same locations o…
We present an approach to learn dense, continuous 2D-3D correspondence distributions over the surface of objects from data with no prior knowledge of visual ambiguities like symmetry. We also present a new method for 6D pose estimation of rigid objects using the learnt distributions to sample, score and refine pose hypotheses. The correspondence distributions are learnt with a contrastive loss, represented in object-specific latent spaces by an encoder-decoder query model and a small fully connected key model. Our method is unsupervised with respect to visual ambiguities, yet we show that the …
Nanjing University of Science and Technology（南京理工大学）
Unsupervised point cloud registration algorithm usually suffers from the unsatisfied registration precision in the partially overlapping problem due to the lack of effective inlier evaluation. In this paper, we propose a neighborhood consensus based reliable inlier evaluation method for robust unsupervised point cloud registration. It is expected to capture the discriminative geometric difference between the source neighborhood and the corresponding pseudo target neighborhood for effective inlier distinction. Specifically, our model consists of a matching map refinement module and an inlier ev…
ETH Zurich（苏黎世联邦理工学院）；University of Amsterdam（阿姆斯特丹大学）；KU Leuven（鲁汶大学）
Monocular depth reconstruction of complex and dynamic scenes is a highly challenging problem. While for rigid scenes learning-based methods have been offering promising results even in unsupervised cases, there exists little to no literature addressing the same for dynamic and deformable scenes. In this work, we present an unsupervised monocular framework for dense depth estimation of dynamic scenes, which jointly reconstructs rigid and non-rigid parts without explicitly modelling the camera motion. Using dense correspondences, we derive a training objective that aims to opportunistically pres…
Monocular depth estimation plays a critical role in various computer vision and robotics applications such as localization, mapping, and 3D object detection. Recently, learning-based algorithms achieve huge success in depth estimation by training models with a large amount of data in a supervised manner. However, it is challenging to acquire dense ground truth depth labels for supervised training, and the unsupervised depth estimation using monocular sequences emerges as a promising alternative. Unfortunately, most studies on unsupervised depth estimation explore loss functions or occlusion ma…
Australian National University（澳大利亚国立大学）；Data61, CSIRO（联邦科学与工业研究组织数据61研究所）
Unsupervised point cloud completion aims to infer the whole geometry of a partial object observation without requiring partial-complete correspondence. Differing from existing deterministic approaches, we advocate generative modeling based unsupervised point cloud completion to explore the missing correspondence. Specifically, we propose a novel framework that performs completion by transforming a partial shape encoding into a complete one using a latent transport module, and it is designed as a latent-space energy-based model (EBM) in an encoder-decoder architecture, aiming to learn a probabi…
Although 3D point cloud data has received widespread attentions as a general form of 3D signal expression, applying point clouds to the task of dense correspondence estimation between 3D shapes has not been investigated widely. Furthermore, even in the few existing 3D point cloud-based methods, an important and widely acknowledged principle, i.e . one-to-one matching, is usually ignored. In response, this paper presents a novel end-to-end learning-based method to estimate the dense correspondence of 3D point clouds, in which the problem of point matching is formulated as a zero-one assignment …
Johns Hopkins University（约翰斯·霍普金斯大学）；Johns Hopkins Medical Institutions（约翰斯·霍普金斯医疗机构）
High-quality 3D reconstructions from endoscopy video play an important role in many clinical applications, including surgical navigation where they enable direct video-CT registration. While many methods exist for general multi-view 3D reconstruction, these methods often fail to deliver satisfactory performance on endoscopic video. Part of the reason is that local descriptors that establish pair-wise point correspondences, and thus drive reconstruction, struggle when confronted with the texture-scarce surface of anatomy. Learning-based dense descriptors usually have larger receptive fields ena…
We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes. We represent the reconstructed surface as an atlas, using a neural network. Using canonical correspondences defined via the atlas, we encourage the reconstruction to be as isometric as possible across frames, leading to semantically-meaningful reconstruction. Through experiments and comparisons, we empirically show that our method achieves results that exceed that state…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）；NVIDIA（英伟达）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）
We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. This is inspired by the observation that view-based surface representations are more effective at modeling high-resolution surface details and texture than their 3D counterparts based on point clouds or voxel occupancy. Specifically, given a 3D shape, we render it from multiple views, and set up a dense correspondence learning task within the contrastive learning framework. As a result, the learned 2D representations are view-invariant and geometrically consistent, leading to better …
Shanghai Research Institute for Intelligent Autonomous Systems（上海智能自主系统研究院）；Shanghai Institute of Intelligent Science and Technology（上海智能科学技术研究院）；State Key Laboratory of Intelligent Autonomous Systems（智能自主系统国家重点实验室）；Frontiers Science Center for Intelligent Autonomous Systems（智能自主系统前沿科学中心）
University of Southern California（南加州大学）；Tencent America（腾讯美国）；Tencent Media Lab（腾讯媒体实验室）
Inspired by the recent PointHop classification method, an unsupervised 3D point cloud registration method, called R-PointHop, is proposed in this work. R-PointHop first determines a local reference frame (LRF) for every point using its nearest neighbors and finds local attributes. Next, R-PointHop obtains local-to-global hierarchical features by point downsampling, neighborhood expansion, attribute construction and dimensionality reduction steps. Thus, point correspondences are built in hierarchical feature space using the nearest neighbor rule. Afterwards, a subset of salient points with good…
City University of Hong Kong（香港城市大学）；Tianjin University（天津大学）
Motivated by the intuition that the critical step of localizing a 2D image in the corresponding 3D point cloud is establishing 2D-3D correspondence between them, we propose the first feature-based dense correspondence framework for addressing the image-to-point cloud registration problem, dubbed CorrI2P, which consists of three modules, i.e., feature embedding, symmetric overlapping region detection, and pose estimation through the established correspondence. Specifically, given a pair of a 2D image and a 3D point cloud, we first transform them into high-dimensional feature space and feed the …
Università degli Studi di Milano（米兰大学）；Universidade NOVA de Lisboa（里斯本新大学）
Ears are a particularly difficult region of the human face to model, not only due to the non-rigid deformations existing between shapes but also to the challenges in processing the retrieved data. The first step towards obtaining a good model is to have complete scans in correspondence, but these usually present a higher amount of occlusions, noise and outliers when compared to most face regions, thus requiring a specific procedure. Therefore, we propose a complete pipeline taking as input unordered 3D point clouds with the aforementioned problems, and producing as output a dataset in correspo…
Equivariant Local Reference Frames for Unsupervised Non-rigid Point Cloud Shape Correspondence
Tsinghua University（清华大学）；Tongji University（同济大学）；Xi’an Research Institute of High-Tech（西安高技术研究所）；University of Hamburg（汉堡大学）；Renmin University of China（中国人民大学）
Establishing dense correspondences between a pair of images is an important and general problem. However, dense flow estimation is often inaccurate in the case of large displacements or homogeneous regions. For most applications and down-stream tasks, such as pose estimation, image manipulation, or 3D reconstruction, it is crucial to know when and where to trust the estimated matches. In this work, we aim to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map indicating the reliability and accuracy of the prediction. We develop a flexible probabilis…
Learning Dense Correspondence for NeRF-Based Face Reenactment
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Nanyang Technological University（南洋理工大学）；SenseTime（商汤科技）
An unsupervised, iterative point-set registration algorithm for an unlabeled (i.e. correspondence between points is unknown) N-dimensional Euclidean point-cloud is proposed. It is based on linear least squares, and considers all possible point pairings and iteratively aligns the two sets until the number of point pairs does not exceed the maximum number of allowable one-to-one pairings.
Nanyang Technological University（南洋理工大学）；Shanghai AI Laboratory（上海人工智能实验室）；SenseTime Research（商汤科技研究院）
This paper presents Dense Siamese Network (DenseSiam), a simple unsupervised learning framework for dense prediction tasks. It learns visual representations by maximizing the similarity between two views of one image with two types of consistency, i.e., pixel consistency and region consistency. Concretely, DenseSiam first maximizes the pixel level spatial consistency according to the exact location correspondence in the overlapped area. It also extracts a batch of region embeddings that correspond to some sub-regions in the overlapped area to be contrasted for region consistency. In contrast t…
In this work, we propose an unsupervised method for learning dense correspondences between shapes using a recent deep functional map framework. Instead of depending on ground-truth correspondences or the computationally expensive geodesic distances, we use heat kernels. These can be computed quickly during training as the supervisor signal. Moreover, we propose a curriculum learning strategy using different heat diffusion times which provide different levels of difficulty during optimization without any sampling mechanism or hard example mining. We present the results of our method on differen…
We explore semantic correspondence estimation through the lens of unsupervised learning. We thoroughly evaluate several recently proposed unsupervised methods across multiple challenging datasets using a standardized evaluation protocol where we vary factors such as the backbone architecture, the pre-training strategy, and the pre-training and finetuning datasets. To better understand the failure modes of these methods, and in order to provide a clearer path for improvement, we provide a new diagnostic framework along with a new performance metric that is better suited to the semantic matching…
We propose a novel unsupervised learning approach to 3D shape correspondence that builds a multiscale matching pipeline into a deep neural network. This approach is based on smooth shells, the current state-of-the-art axiomatic correspondence method, which requires an a priori stochastic search over the space of initial poses. Our goal is to replace this costly preprocessing step by directly learning good initializations from the input surfaces. To that end, we systematically derive a fully differentiable, hierarchical matching pipeline from entropy regularized optimal transport. This allows u…
Computer Vision Lab, ETH Zurich（苏黎世联邦理工学院计算机视觉实验室）
The key challenge in learning dense correspondences lies in the lack of ground-truth matches for real image pairs. While photometric consistency losses provide unsupervised alternatives, they struggle with large appearance changes, which are ubiquitous in geometric and semantic matching tasks. Moreover, methods relying on synthetic training pairs often suffer from poor generalisation to real data. We propose Warp Consistency, an unsupervised learning objective for dense correspondence regression. Our objective is effective even in settings with large appearance and view-point changes. Given a …
College of Computer Science, Sichuan University（四川大学计算机科学学院）；Centre for Frontier AI Research (CFAR), A*STAR（新加坡科技研究局前沿人工智能研究中心）
Cross-domain image retrieval aims at retrieving images across different domains to excavate cross-domain classificatory or correspondence relationships. This paper studies a less-touched problem of cross-domain image retrieval, i.e., unsupervised cross-domain image retrieval, considering the following practical assumptions: (i) no correspondence relationship, and (ii) no category annotations. It is challenging to align and bridge distinct domains without cross-domain correspondence. To tackle the challenge, we present a novel Correspondence-free Domain Alignment (CoDA) method to effectively el…
Facebook AI Research（脸书人工智能研究院）；Technical University of Munich（慕尼黑工业大学）
We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes and produces in one go, i.e. in a single feed forward pass, a smooth interpolation and point-to-point correspondences between them. The interpolation, expressed as a deformation field, changes the pose of the source shape to resemble the target, but leaves the object identity unchanged. NeuroMorph uses an elegant architecture combining graph convolutions with global feature pooling to extract local features. During training, the model is incentivized to create realistic deformations by approximating geod…
Beijing Institute of Technology（北京理工大学）；The University of Adelaide（阿德莱德大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）
We propose a fast, accurate matching method for estimating dense pixel correspondences across scenes. It is a challenging problem to estimate dense pixel correspondences between images depicting different scenes or instances of the same object category. While most such matching methods rely on hand-crafted features such as SIFT, we learn features from a large amount of unlabeled image patches using unsupervised learning. Pixel-layer features are obtained by encoding over the dictionary, followed by spatial pooling to obtain patch-layer features. The learned features are then seamlessly embedde…
College of Electronic Science and Technology, Nation University of Defense Technology (NUDT)（国防科技大学电子科学学院）；School of Electronics and Communication Engineering, Sun Yat-sen University（中山大学电子与通信工程学院）
Stereo image pairs encode 3D scene cues into stereo correspondences between the left and right images. To exploit 3D cues within stereo images, recent CNN based methods commonly use cost volume techniques to capture stereo correspondence over large disparities. However, since disparities can vary significantly for stereo cameras with different baselines, focal lengths and resolutions, the fixed maximum disparity used in cost volume techniques hinders them to handle different stereo image pairs with large disparity variations. In this paper, we propose a generic parallax-attention mechanism (PA…
Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. To solve this task, algorithms must produce features for every pixel that are both semantically meaningful and compact enough to form distinct clusters. Unlike previous works which achieve this with a single end-to-end framework, we propose to separate feature learning from cluster compactification. Empirically, we show that current unsupervised feature learning frameworks already generate dense features whose correlations are semantically con…
Element AI；Cornell University（康奈尔大学）；Mila；Université de Montréal（蒙特利尔大学）
Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e., compositions of data augmentation) of the same image. However, many visual understanding tasks require dense (pixel-level) representations. In this paper, we propose View-Agnostic Dense Representation (VADeR) for unsupervised learning of dense representations. VADeR learns pixelwise representations by forcing local features to remain constant over different viewi…
State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所机器人学国家重点实验室）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Shape correspondence from 3D deformation learning has attracted appealing academy interests recently. Nevertheless, current deep learning based methods require the supervision of dense annotations to learn per-point translations, which severely overparameterize the deformation process. Moreover, they fail to capture local geometric details of original shape via global feature embedding. To address these challenges, we develop a new Unsupervised Dense Deformation Embedding Network (i.e., UD^2E-Net), which learns to predict deformations between non-rigid shapes from dense local features. Since i…
Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；Department of Computer Science and Information Engineering, National Taiwan University（国立台湾大学资讯工程学系）
With the aim to improve the performance of feature matching, we present an unsupervised approach to fuse various local descriptors in the space of homographies. Inspired by the observation that the homographies of correct feature correspondences vary smoothly along the spatial domain, our approach stands on the unsupervised nature of feature matching, and can select a good descriptor for matching each feature point. Specifically, the homography space serves as the common domain, in which a correspondence obtained by any descriptor is considered as a point, for integrating various heterogeneous…
The Hong Kong University of Science and Technology（香港科技大学）
Registration of pre-operative and post-recurrence brain images is often needed to evaluate the effectiveness of brain gliomas treatment. While recent deep learning-based deformable registration methods have achieved remarkable success with healthy brain images, most of them would be unable to accurately align images with pathologies due to the absent correspondences in the reference image. In this paper, we propose a deep learning-based deformable registration method that jointly estimates regions with absent correspondence and bidirectional deformation fields. A forward-backward consistency c…
