Symmetry Detection of Occluded Point Cloud Using Deep Learning
Shenzhen Institute of Advanced Technology, Chinese Academy of Science（中国科学院深圳先进技术研究院）；China Telecom Tech Division Hunan（中国电信湖南技术分部）；Yale University（耶鲁大学）
Symmetry detection has been a classical problem in computer graphics, many of which using traditional geometric methods. In recent years, however, we have witnessed the arising deep learning changed the landscape of computer graphics. In this paper, we aim to solve the symmetry detection of the occluded point cloud in a deep-learning fashion. To the best of our knowledge, we are the first to utilize deep learning to tackle such a problem. In such a deep learning framework, double supervisions: points on the symmetry plane and normal vectors are employed to help us pinpoint the symmetry plane. We conducted experiments on the YCB- video dataset and demonstrate the efficacy of our method.
Gap Completion in Point Cloud Scene occluded by Vehicles using SGC-Net
Chair of Cartography and Visual Analytics, Technical University of Munich（慕尼黑工业大学制图与视觉分析主席）；Institute of Cartography and Geoinformatics, Leibniz University Hannover（汉诺威莱布尼茨大学制图与地理信息研究所）；Computer Vision Group, Technical University of Munich（慕尼黑工业大学计算机视觉组）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
One major challenge in 3D reconstruction is to infer the complete shape geometry from partial foreground occlusions. In this paper, we propose a method to reconstruct the complete 3D shape of an object from a single RGB image, with robustness to occlusion. Given the image and a silhouette of the visible region, our approach completes the silhouette of the occluded region and then generates a point cloud. We show improvements for reconstruction of non-occluded and partially occluded objects by providing the predicted complete silhouette as guidance. We also improve state-of-the-art for 3D shape…
Understanding the flow in 3D space of sparsely sampled points between two consecutive time frames is the core stone of modern geometric-driven systems such as VR/AR, Robotics, and Autonomous driving. The lack of real, non-simulated, labeled data for this task emphasizes the importance of self- or un-supervised deep architectures. This work presents a new self-supervised training method and an architecture for the 3D scene flow estimation under occlusions. Here we show that smart multi-layer fusion between flow prediction and occlusion detection outperforms traditional architectures by a large …
With the fast growth of immersive video sequences, achieving seamless and high-quality compressed 3D content is even more critical. MPEG recently developed a video-based point cloud compression (V-PCC) standard for dynamic point cloud coding. However, reconstructed point clouds using V-PCC suffer from different artifacts, including losing data during pre-processing before applying existing video coding techniques, e.g., High-Efficiency Video Coding (HEVC). Patch generations and self-occluded points in the 3D to the 2D projection are the main reasons for missing data using V-PCC. This paper pro…
University of Cambridge（剑桥大学）；University of Oxford（牛津大学）；UC Berkeley（加州大学伯克利分校）；University College London（伦敦大学学院）
We describe a simple pre-training approach for point clouds. It works in three steps: 1. Mask all points occluded in a camera view; 2. Learn an encoder-decoder model to reconstruct the occluded points; 3. Use the encoder weights as initialisation for downstream point cloud tasks. We find that even when we construct a single pre-training dataset (from ModelNet40), this pre-training method improves accuracy across different datasets and encoders, on a wide range of downstream tasks. Specifically, we show that our method outperforms previous pre-training methods in object classification, and both…
When navigating in urban environments, many of the objects that need to be tracked and avoided are heavily occluded. Planning and tracking using these partial scans can be challenging. The aim of this work is to learn to complete these partial point clouds, giving us a full understanding of the object's geometry using only partial observations. Previous methods achieve this with the help of complete, ground-truth annotations of the target objects, which are available only for simulated datasets. However, such ground truth is unavailable for real-world LiDAR data. In this work, we present a sel…
We present MoRig, a method that automatically rigs character meshes driven by single-view point cloud streams capturing the motion of performing characters. Our method is also able to animate the 3D meshes according to the captured point cloud motion. MoRig's neural network encodes motion cues from the point clouds into features that are informative about the articulated parts of the performing character. These motion-aware features guide the inference of an appropriate skeletal rig for the input mesh, which is then animated based on the point cloud motion. Our method can rig and animate diver…
Recognition of occluded objects in unseen indoor environments is a challenging problem for mobile robots. This work proposes a new slicing-based topological descriptor that captures the 3D shape of object point clouds to address this challenge. It yields similarities between the descriptors of the occluded and the corresponding unoccluded objects, enabling object unity-based recognition using a library of trained models. The descriptor is obtained by partitioning an object's point cloud into multiple 2D slices and constructing filtrations (nested sequences of simplicial complexes) on the slice…
Three-dimentional reconstruction of complex, dynamic population canopy architecture for crops with a novel point cloud completion model: A case study in Brassica napus rapeseed
PASR: Pose-Aware 3D Shape Retrieval from Occluded Single Views
Shanghai Jiao Tong University（上海交通大学）；Johns Hopkins University（约翰霍普金斯大学）；University of California, San Diego（加州大学圣地亚哥分校）；CISPA Helmholtz Center for Information Security（CISPA海德堡信息安全中心）
South China University of Technology（华南理工大学）；Peng Cheng Laboratory（鹏城实验室）
The challenges of learning a robust 6D pose function lie in 1) severe occlusion and 2) systematic noises in depth images. Inspired by the success of point-pair features, the goal of this paper is to recover the 6D pose of an object instance segmented from RGB-D images by locally matching pairs of oriented points between the model and camera space. To this end, we propose a novel Bi-directional Correspondence Mapping Network (BiCo-Net) to first generate point clouds guided by a typical pose regression, which can thus incorporate pose-sensitive information to optimize generation of local coordin…
3D scene flow estimation is a vital tool in perceiving our environment given depth or range sensors. Unlike optical flow, the data is usually sparse and in most cases partially occluded in between two temporal samplings. Here we propose a new scene flow architecture called OGSF-Net which tightly couples the learning for both flow and occlusions between frames. Their coupled symbiosis results in a more accurate prediction of flow in space. Unlike a traditional multi-action network, our unified approach is fused throughout the network, boosting performances for both occlusion detection and flow …
3D reconstruction from single view images is an ill-posed problem. Inferring the hidden regions from self-occluded images is both challenging and ambiguous. We propose a two-pronged approach to address these issues. To better incorporate the data prior and generate meaningful reconstructions, we propose 3D-LMNet, a latent embedding matching approach for 3D reconstruction. We first train a 3D point cloud auto-encoder and then learn a mapping from the 2D image to the corresponding learnt embedding. To tackle the issue of uncertainty in the reconstruction, we predict multiple reconstructions that…
Static gesture recognition is an effective non-verbal communication channel between a user and their devices; however many modern methods are sensitive to the relative pose of the user's hands with respect to the capture device, as parts of the gesture can become occluded. We present two methodologies for gesture recognition via synchronized recording from two depth cameras to alleviate this occlusion problem. One is a more classic approach using iterative closest point registration to accurately fuse point clouds and a single PointNet architecture for classification, and the other is a dual P…
In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches to addressing this task have shown great success on synthetic datasets, we have observed them to fail in the presence of real-world data. We thus analyze the causes of these failures, which we trace back to the difference between the feature distributions of the source and target point clouds, and the sensitivity of the widely-used SVD-based loss function to the range of rotation between the two point clouds. We address the first challenge by introducing a new n…
Efficient 3D Perception on Multi-Sweep Point Cloud with Gumbel Spatial Pruning
Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Department of Computer Science and Engineering, Beihang University（北航计算机科学与工程学院）；Noah’s Ark Lab（诺亚实验室）；Department of Computer Science, University of Hong Kong（香港大学计算机科学系）
Elektrobit Automotive（Elektrobit汽车公司）；Transilvania University of Brasov（布拉索夫特兰西瓦尼亚大学）
In this paper, we propose an object reconstruction apparatus that uses the so-called Generic Primitives (GP) to complete shapes. A GP is a 3D point cloud depicting a generalized shape of a class of objects. To reconstruct the objects in a scene we first fit a GP onto each occluded object to obtain an initial raw structure. Secondly, we use a model-based deformation technique to fold the surface of the GP over the occluded object. The deformation model is encoded within the layers of a Deep Neural Network (DNN), coined GFPNet. The objective of the network is to transfer the particularities of t…
Ulm University（乌尔姆大学）；University College London（伦敦大学学院）；Linköping University（林雪平大学）
We suggest a method to directly deep-learn light transport, i. e., the mapping from a 3D geometry-illumination-material configuration to a shaded 2D image. While many previous learning methods have employed 2D convolutional neural networks applied to images, we show for the first time that light transport can be learned directly in 3D. The benefit of 3D over 2D is, that the former can also correctly capture illumination effects related to occluded and/or semi-transparent geometry. To learn 3D light transport, we represent the 3D scene as an unstructured 3D point cloud, which is later, during r…
Jeonbuk National University（全北国立大学）；Kyungpook National University（庆北国立大学）
A laser scanner can easily acquire the geometric data of physical environments in the form of a point cloud. Recognizing objects from a point cloud is often required for industrial 3D reconstruction, which should include not only geometry information but also semantic information. However, recognition process is often a bottleneck in 3D reconstruction because it requires expertise on domain knowledge and intensive labor. To address this problem, various methods have been developed to recognize objects by retrieving the corresponding model in the database from an input geometry query. In recent…
CSIRO Data61（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）
Multiview detection uses multiple calibrated cameras with overlapping fields of views to locate occluded pedestrians. In this field, existing methods typically adopt a ``human modeling - aggregation'' strategy. To find robust pedestrian representations, some intuitively incorporate 2D perception results from each frame, while others use entire frame features projected to the ground plane. However, the former does not consider the human appearance and leads to many ambiguities, and the latter suffers from projection errors due to the lack of accurate height of the human torso and head. In this …
LIX, Ecole Polytechnique, IP Paris（巴黎理工学院综合理工学院计算机科学实验室）
Despite the success of deep functional maps in non-rigid 3D shape matching, there exists no learning framework that models both self-symmetry and shape matching simultaneously. This is despite the fact that errors due to symmetry mismatch are a major challenge in non-rigid shape matching. In this paper, we propose a novel framework that simultaneously learns both self symmetry as well as a pairwise map between a pair of shapes. Our key idea is to couple a self symmetry map and a pairwise map through a regularization term that provides a joint constraint on both of them, thereby, leading to mor…
Dalian University of Technology（大连理工大学）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong (ShenZhen)（香港中文大学（深圳））；Princeton University（普林斯顿大学）
We present a deep reinforcement learning method of progressive view inpainting for colored semantic point cloud scene completion under volume guidance, achieving high-quality scene reconstruction from only a single RGB-D image with severe occlusion. Our approach is end-to-end, consisting of three modules: 3D scene volume reconstruction, 2D RGB-D and segmentation image inpainting, and multi-view selection for completion. Given a single RGB-D image, our method first predicts its semantic segmentation map and goes through the 3D volume branch to obtain a volumetric scene reconstruction as a guide…
Rotational Symmetry based Object Pose Estimation from Point Clouds in the Absence of Known 3D Models
Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, School of Computer Science, Hangzhou Dianzi University（浙江省脑机协同智能重点实验室，杭州电子科技大学计算机学院）；Advanced Intelligent Manufacturing Research Group, the University of Nottingham Ningbo China（先进智能制造研究组，宁波诺丁汉大学）
Tsinghua University（清华大学）；JD Logistics, JD.com（京东集团京东物流）；New York University（纽约大学）；Wayne State University（韦恩州立大学）
The manual annotation for large-scale point clouds is still tedious and unavailable for many harsh real-world tasks. Self-supervised learning, which is used on raw and unlabeled data to pre-train deep neural networks, is a promising approach to address this issue. Existing works usually take the common aid from auto-encoders to establish the self-supervision by the self-reconstruction schema. However, the previous auto-encoders merely focus on the global shapes and do not distinguish the local and global geometric features apart. To address this problem, we present a novel and efficient self-s…
Object shape is a key cue that contributes to the semantic understanding of objects. In this work we focus on the categorization of real-world object point clouds to particular shape types. Therein surface description and representation of object shape structure have significant influence on shape categorization accuracy, when dealing with real-world scenes featuring noisy, partial and occluded object observations. An unsupervised hierarchical learning procedure is utilized here to symbolically describe surface characteristics on multiple semantic levels. Furthermore, a constellation model is …
This paper presents a neural-network-based solution to recover pixels occluded by clouds in satellite images. We leverage radio frequency (RF) signals in the ultra/super-high frequency band that penetrate clouds to help reconstruct the occluded regions in multispectral images. We introduce the first multi-modal multi-temporal cloud removal model. Our model uses publicly available satellite observations and produces daily cloud-free images. Experimental results show that our system significantly outperforms baselines by 8dB in PSNR. We also demonstrate use cases of our system in digital agricul…
Huazhong University of Science & Technology（华中科技大学）；Horizon Robotics（地平线机器人）
Studying the inherent symmetry of data is of great importance in machine learning. Point cloud, the most important data format for 3D environmental perception, is naturally endowed with strong radial symmetry. In this work, we exploit this radial symmetry via a divide-and-conquer strategy to boost 3D perception performance and ease optimization. We propose Azimuth Normalization (AziNorm), which normalizes the point clouds along the radial direction and eliminates the variability brought by the difference of azimuth. AziNorm can be flexibly incorporated into most LiDAR-based perception methods.…
College of Information Sciences and Technology, Donghua University（东华大学信息科学与技术学院）；Engineering Research Center of Digitized Textile & Fashion Technology, Ministry of Education, Donghua University（东华大学数字化纺织服装技术教育部工程研究中心）
Automatic leaf segmentation, as well as identification and classification methods that built upon it, are able to provide immediate monitoring for plant growth status to guarantee the output. Although 3D plant point clouds contain abundant phenotypic features, plant leaves are usually distributed in clusters and are sometimes seriously overlapped in the canopy. Therefore, it is still a big challenge to automatically segment each individual leaf from a highly crowded plant canopy in 3D for plant phenotyping purposes. In this work, we propose an overlapping-free individual leaf segmentation meth…
Huazhong University of Science and Technology（华中科技大学）；Nanyang Technological University（南洋理工大学）
We study the problem of novel view synthesis of objects from a single image. Existing methods have demonstrated the potential in single-view view synthesis. However, they still fail to recover the fine appearance details, especially in self-occluded areas. This is because a single view only provides limited information. We observe that manmade objects usually exhibit symmetric appearances, which introduce additional prior knowledge. Motivated by this, we investigate the potential performance gains of explicitly embedding symmetry into the scene representation. In this paper, we propose SymmNeR…
The Machine Learning Lab at Ukrainian Catholic University（乌克兰天主教大学机器学习实验室）；SoftServe Inc.（SoftServe 公司）
3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, specific properties of the object surface, imperfect reconstruction algorithms, etc. Point cloud completion is specifically designed to fill in the missing parts of the object and obtain its high-quality 3D representation. The existing completion approaches perform well on the academic datasets with a predefined set of object classes and very specific types of defects; however, their performance drops significantly in …
A Multi-View High-Resolution Foot-Ankle Complex Point Cloud Dataset During Gait for Occlusion-Robust 3D Completion
College of Biomedical Engineering（生物医学工程学院）；College of Computer Science and Artificial Intelligence（计算机科学与人工智能学院）；Department of Information Engineering（信息工程系）；School of Computer Science and Engineering（计算机科学与工程学院）
Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy
Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
