We propose a deep autoencoder with graph topology inference and filtering to achieve compact representations of unorganized 3D point clouds in an unsupervised manner. Many previous works discretize 3D points to voxels and then use lattice-based methods to process and learn 3D spatial information; however, this leads to inevitable discretization errors. In this work, we handle raw 3D points without such compromise. The proposed networks follow the autoencoder framework with a focus on designing the decoder. The encoder adopts similar architectures as in PointNet. The decoder involves three novel modules. The folding module folds a canonical 2D lattice to the underlying surface of a 3D point cloud, achieving coarse reconstruction; the graph-topology-inference module learns a graph topology to represent pairwise relationships between 3D points, pushing the latent code to preserve both coordinates and pairwise relationships of points in 3D point clouds; and the graph-filtering module couples the above two modules, refining the coarse reconstruction through a learnt graph topology to obtain the final reconstruction. The proposed decoder leverages a learnable graph topology to push the codeword to preserve representative features and further improve the unsupervised-learning performance. We further provide theoretical analyses of the proposed architecture. In the experiments, we validate the proposed networks in three tasks, including 3D point cloud reconstruction, visualization, and transfer classification. The experimental results show that (1) the proposed networks outperform the state-of-the-art methods in various tasks; (2) a graph topology can be inferred as auxiliary information without specific supervision on graph topology inference; and (3) graph filtering refines the reconstruction, leading to better performances.
Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition
Pengcheng Laboratory（鹏城实验室）；School of Electronic and Information Engineering, South China University of Technology（华南理工大学电子与信息学院）；Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen)（香港中文大学（深圳））；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
We present a method for inferring dense depth maps from images and sparse depth measurements by leveraging synthetic data to learn the association of sparse point clouds with dense natural shapes, and using the image as evidence to validate the predicted depth map. Our learned prior for natural shapes uses only sparse depth as input, not images, so the method is not affected by the covariate shift when attempting to transfer learned models from synthetic data to real ones. This allows us to use abundant synthetic data with ground truth to learn the most difficult component of the reconstructio…
Northwestern Polytechnical University（西北工业大学）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Semantic 3D keypoints are category-level semantic consistent points on 3D objects. Detecting 3D semantic keypoints is a foundation for a number of 3D vision tasks but remains challenging, due to the ambiguity of semantic information, especially when the objects are represented by unordered 3D point clouds. Existing unsupervised methods tend to generate category-level keypoints in implicit manners, making it difficult to extract high-level information, such as semantic labels and topology. From a novel mutual reconstruction perspective, we present an unsupervised method to generate consistent s…
An unsupervised shape analysis is proposed to learn concepts reflecting shape commonalities. Our approach is two-fold: i) a spatial topology analysis of point cloud segment constellations within objects is used in which constellations are decomposed and described in a hierarchical and symbolic manner. ii) A topology analysis of the description space is used in which segment decompositions are exposed in. Inspired by Persistent Homology, groups of shape commonality are revealed. Experiments show that extracted persistent commonality groups can feature semantically meaningful shape concepts; the…
Reliable knowledge of road boundaries is critical for autonomous vehicle navigation. We propose a robust curb detection and filtering technique based on the fusion of camera semantics and dense lidar point clouds. The lidar point clouds are collected by fusing multiple lidars for robust feature detection. The camera semantics are based on a modified EfficientNet architecture which is trained with labeled data collected from onboard fisheye cameras. The point clouds are associated with the closest curb segment with $L_2$-norm analysis after projecting into the image space with the fisheye model…
Unsupervised domain adaptation (UDA) deals with the adaptation of models from a given source domain with labeled data to an unlabeled target domain. In this paper, we utilize the inherent prediction uncertainty of a model to accomplish the domain adaptation task. The uncertainty is measured by Monte-Carlo dropout and used for our proposed Uncertainty-based Filtering and Feature Alignment (UFAL) that combines an Uncertain Feature Loss (UFL) function and an Uncertainty-Based Filtering (UBF) approach for alignment of features in Euclidean space. Our method surpasses recently proposed architecture…
A point cloud serves as a representation of the surface of a three-dimensional (3D) shape. Deep generative models have been adapted to model their variations typically using a map from a ball-like set of latent variables. However, previous approaches did not pay much attention to the topological structure of a point cloud, despite that a continuous map cannot express the varying numbers of holes and intersections. Moreover, a point cloud is often composed of multiple subparts, and it is also difficult to express. In this study, we propose ChartPointFlow, a flow-based generative model with mult…
We describe a method to infer dense depth from camera motion and sparse depth as estimated using a visual-inertial odometry system. Unlike other scenarios using point clouds from lidar or structured light sensors, we have few hundreds to few thousand points, insufficient to inform the topology of the scene. Our method first constructs a piecewise planar scaffolding of the scene, and then uses it to infer dense depth using the image along with the sparse points. We use a predictive cross-modal criterion, akin to `self-supervision,' measuring photometric consistency across time, forward-backward…
Autonomous camera systems are often subjected to an optimization/filtering operation to smoothen and stabilize the rough trajectory estimates. Most common filtering techniques do reduce the irregularities in data; however, they fail to mimic the behavior of a human cameraman. Global filtering methods modeling human camera operators have been successful; however, they are limited to offline settings. In this paper, we propose two online filtering methods called Cinefilters, which produce smooth camera trajectories that are motivated by cinematographic principles. The first filter (CineConvex) u…
Unsupervised Unfolded rPCA (U2-rPCA): Deep Interpretable Clutter Filtering for Ultrasound Microvascular Imaging
Fujian Key Laboratory of Urban Intelligent Sensing and Computing, School of Informatics, Xiamen University（福建城市智能感知与计算重点实验室，信息学院，厦门大学）；School of Electronic Science and Engineering, Fujian Provincial Key Laboratory of Plasma and Magnetic Resonance, Xiamen University（电子科学与技术学院，福建省等离子体与磁共振重点实验室，厦门大学）；Department of Computer Science and Technology, School of Informatics, and the National Institute for Data Science in Health and Medicine, Xiamen University（计算机科学与技术系，信息学院，以及健康医学数据科学国家研究院，厦门大学）
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation
Hangzhou Dianzi University（杭州电子科技大学）；Macao Polytechnic University（澳门理工大学）；Beijing Institute of Technology（北京理工大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Technical University Munich（慕尼黑工业大学）；OneProjects Design Innovation GmbH（OneProjects设计创新有限责任公司）
In ultrasound imaging the appearance of homogeneous regions of tissue is subject to speckle, which for certain applications can make the detection of tissue irregularities difficult. To cope with this, it is common practice to apply speckle reduction filters to the images. Most conventional filtering techniques are fairly hand-crafted and often need to be finely tuned to the present hardware, imaging scheme and application. Learning based techniques on the other hand suffer from the need for a target image for training (in case of fully supervised techniques) or require narrow, complex physics…
The goal of this paper is to learn dense 3D shape correspondence for topology-varying objects in an unsupervised manner. Conventional implicit functions estimate the occupancy of a 3D point given a shape latent code. Instead, our novel implicit function produces a part embedding vector for each 3D point, which is assumed to be similar to its densely corresponded point in another 3D shape of the same object category. Furthermore, we implement dense correspondence through an inverse function mapping from the part embedding to a corresponded 3D point. Both functions are jointly learned with sever…
Unified Unsupervised Anomaly Detection via Matching Cost Filtering
State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China（合成过程工业综合自动化国家重点实验室，东北大学，沈阳，中国）；University of Surrey（Surrey大学）；School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Computer Science, The University of Adelaide（阿德莱德大学计算机学院）；College of Computing & Data Science, Nanyang Technological University（南洋理工大学计算机与数据科学学院）；Surrey Institute for People-Centred Artificial Intelligence, and Centre for Vision, Speech and Signal Processing, University of Surrey（Surrey人本人工智能研究所，以及视觉、语音和信号处理中心，Surrey大学）
A novel solution for the content-based 3D shape retrieval problem using an unsupervised clustering approach, which does not need any label information of 3D shapes, is presented in this work. The proposed shape retrieval system consists of two modules in cascade: the irrelevance filtering (IF) module and the similarity ranking (SR) module. The IF module attempts to cluster gallery shapes that are similar to each other by examining global and local features simultaneously. However, shapes that are close in the local feature space can be distant in the global feature space, and vice versa. To re…
Beyond Heatmaps: Unsupervised Concept-Graph Reasoning for Interpretable Visual Explanation
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Saarland University（萨尔大学）；Oldenburg University（奥尔登堡大学）；BEGO GmbH & Co. KG（BEGO有限两合公司）
Fast Diffeomorphic Image Registration using Patch based Fully Convolutional Networks
School of Computer and Electrical Engineering, Hunan University of Arts and Science（湖南文理学院计算机与电气工程学院）；Furong College, Hunan University of Arts and Science（湖南文理学院芙蓉学院）；The University of Hong Kong（香港大学）
Hamamatsu Photonics K. K.（滨松光子学株式会社）；Hamamatsu University School of Medicine（滨松医科大学）
Although supervised convolutional neural networks (CNNs) often outperform conventional alternatives for denoising positron emission tomography (PET) images, they require many low- and high-quality reference PET image pairs. Herein, we propose an unsupervised 3D PET image denoising method based on an anatomical information-guided attention mechanism. The proposed magnetic resonance-guided deep decoder (MR-GDD) utilizes the spatial details and semantic features of MR-guidance image more effectively by introducing encoder-decoder and deep decoder subnetworks. Moreover, the specific shapes and pat…
Korea Advanced Institute of Science and Technology（韩国科学技术院）；The Catholic University of Korea（韩国加图立大学）；University of Ulsan College of Medicine（蔚山大学医学院）；Asan Medical Center（峨山医疗中心）；Korea Automotive Technology Institute（韩国汽车技术研究院）
Image registration is a fundamental task in medical image analysis. Recently, deep learning based image registration methods have been extensively investigated due to their excellent performance despite the ultra-fast computational time. However, the existing deep learning methods still have limitation in the preservation of original topology during the deformation with registration vector fields. To address this issues, here we present a cycle-consistent deformable image registration. The cycle consistency enhances image registration performance by providing an implicit regularization to pres…
University of Electronic Science and Technology of China（电子科技大学）；Chongqing Changan Automobile Co., Ltd（重庆长安汽车股份有限公司）
With the explosive growth of multi-source data, multi-view clustering has attracted great attention in recent years. Most existing multi-view methods operate in raw feature space and heavily depend on the quality of original feature representation. Moreover, they are often designed for feature data and ignore the rich topology structure information. Accordingly, in this paper, we propose a generic framework to cluster both attribute and graph data with heterogeneous features. It is capable of exploring the interplay between feature and structure. Specifically, we first adopt graph filtering te…
