Learning a Structured Latent Space for Unsupervised Point Cloud Completion

In this paper we study the task of a single-view image-guided point cloud completion. Existing methods have got promising results by fusing the information of image into point cloud explicitly or implicitly. However, given that the image has global shape information and the partial point cloud has rich local details, We believe that both modalities need to be given equal attention when performing modality fusion. To this end, we propose a novel dual-channel modality fusion network for image-guided point cloud completion(named DMF-Net), in a coarse-to-fine manner. In the first stage, DMF-Net takes a partial point cloud and corresponding image as input to recover a coarse point cloud. In the second stage, the coarse point cloud will be upsampled twice with shape-aware upsampling transformer to get the dense and complete point cloud. Extensive quantitative and qualitative experimental results show that DMF-Net outperforms the state-of-the-art unimodal and multimodal point cloud completion works on ShapeNet-ViPC dataset.

SPC: Self-supervised point cloud completion.

Point cloud classification is critical for three-dimensional scene understanding. However, in real-world scenarios, depth cameras often capture partial, single-view point clouds of objects with different poses, making their accurate classification a challenge. In this paper, we propose a novel point cloud classification network that captures the detailed spatial structure of objects by constructing tetrahedra, which is different from point-wise operations. Specifically, we propose a RISpaNet block to extract rotation-invariant features. A rotation-invariant property generation module is designed in RISpaNet for constructing rotation-invariant tetrahedron properties (RITPs). Meanwhile, a multi-scale pooling module and a hybrid encoder are used to process RITPs to generate integrated rotation-invariant features. Further, for single-view point clouds, a complete point cloud auxiliary branch and a part-whole correlation module are jointly employed to obtain complete point cloud features from partial point clouds. Experimental results show that this network performs better than other state-of-the-art methods, evaluated on four public datasets. We achieved an overall accuracy of 94.7% (+2.0%) on ModelNet40, 93.4% (+5.9%) on MVP, 94.7% (+6.3%) on PCN and 94.8% (+1.7%) on ScanObjectNN. Our project website is https://luxurylf.github.io/RISpaNet_project/.

We consider the problem of online and real-time registration of partial point clouds obtained from an unseen real-world rigid object without knowing its 3D model. The point cloud is partial as it is obtained by a depth sensor capturing only the visible part of the object from a certain viewpoint. It introduces two main challenges: 1) two partial point clouds do not fully overlap and 2) keypoints tend to be less reliable when the visible part of the object does not have salient local structures. To address these issues, we propose DeepPRO, a keypoint-free and an end-to-end trainable deep neural network. Its core idea is inspired by how humans align two point clouds: we can imagine how two point clouds will look like after the registration based on their shape. To realize the idea, DeepPRO has inputs of two partial point clouds and directly predicts the point-wise location of the aligned point cloud. By preserving the ordering of points during the prediction, we enjoy dense correspondences between input and predicted point clouds when inferring rigid transform parameters. We conduct extensive experiments on the real-world Linemod and synthetic ModelNet40 datasets. In addition, we collect and evaluate on the PRO1k dataset, a large-scale version of Linemod meant to test generalization to real-world scans. Results show that DeepPRO achieves the best accuracy against thirteen strong baseline methods, e.g., 2.2mm ADD on the Linemod dataset, while running 50 fps on mobile devices.

Point cloud is the popular researches in the industry, and the research on partial point cloud is favored by many researchers. In the acquisition process of original 3D point cloud data, there are partial or sparse problems due to occlusion, lighting and other reasons, which will lead to deviation in downstream tasks. We propose a network MDPCN using multiple decoders, which can make the partial point cloud complete. The network uses deep learning to get multiple features of the partial point cloud, and uses multiple identical decoders to decode. Each decoder uses the self-attention module and the Folding-Net to generate smooth point clouds from the features, and finally integrates the point clouds generated by each decoder to obtain dense point cloud. Compared with other mainstream point cloud completion network methods and ablation experiments, it can be proved that this network model can generate more accurate point cloud and effectively complete the 3D reconstruction task.

Self-supervised learning on point clouds has gained a lot of attention recently, since it addresses the label-efficiency and domain-gap problems on point cloud tasks. In this paper, we propose a novel self-supervised framework to learn informative features from partial point clouds. We leverage partial point clouds scanned by LiDAR that contain both content and pose attributes, and we show that disentangling such two factors from partial point clouds enhances feature learning. To this end, our framework consists of three main parts: 1) a completion network to capture holistic semantics of point clouds; 2) a pose regression network to understand the viewing angle where partial data is scanned from; 3) a partial reconstruction network to encourage the model to learn content and pose features. To demonstrate the robustness of the learnt feature representations, we conduct several downstream tasks including classification, part segmentation, and registration, with comparisons against state-of-the-art methods. Our method not only outperforms existing self-supervised methods, but also shows a better generalizability across synthetic and real-world datasets.

Point cloud completion aims at completing geometric and topological shapes from a partial observation. However, some topology of the original shape is missing, existing methods directly predict the location of complete points, without predicting structured and topological information of the complete shape, which leads to inferior performance. To better tackle the missing topology part, we propose LAKe-Net, a novel topology-aware point cloud completion model by localizing aligned keypoints, with a novel Keypoints-Skeleton-Shape prediction manner. Specifically, our method completes missing topology using three steps: 1) Aligned Keypoint Localization. An asymmetric keypoint locator, including an unsupervised multi-scale keypoint detector and a complete keypoint generator, is proposed for localizing aligned keypoints from complete and partial point clouds. We theoretically prove that the detector can capture aligned keypoints for objects within a sub-category. 2) Surface-skeleton Generation. A new type of skeleton, named Surface-skeleton, is generated from keypoints based on geometric priors to fully represent the topological information captured from keypoints and better recover the local details. 3) Shape Refinement. We design a refinement subnet where multi-scale surface-skeletons are fed into each recursive skeleton-assisted refinement module to assist the completion process. Experimental results show that our method achieves the state-of-the-art performance on point cloud completion.

Partial point cloud registration is an essential and fundamental component of generating complete 3D shapes, aiming at converting partial scans into a unified coordinate system. However, existing point cloud registration methods suffer from inadequately rich local feature extraction and feature interaction. In addition, these methods still face challenges in modeling the global contextual information of point clouds sufficiently, which limits the improvement in registration effectiveness, especially for partial-to-partial point cloud registration with high noise. To overcome these issues, this paper proposes an enhanced PointNet and assignable weights transformer network (LFA-Net) for partial point cloud registration. The model achieves coarse-to-fine point cloud registration through three core modules. First, the Sufficient Local Feature Extraction Module (LFM) is constructed to extract various local feature information. Then, the Adequate Feature Aggregation Module (FAM) is designed to integrate the feature information from different point clouds. Finally, the Assignable Weights Transformer Module (ATM) is presented to stimulate the model’s global modeling ability during the registration process, enabling the selection of representative points for optimal point cloud registration. Extensive experiments conducted on ModelNet40 using partially overlapping point clouds illustrate the superior registration performance of LFA-Net compared with other state-of-the-art methods. Moreover, Numerous experiments on synthetic and real-word datasets further indicate that LFA-Net also has significant advantages in registering partial point clouds with noise and unseen categories, which demonstrates its excellent robustness and generalization ability for real-world practical application.

Rigid registration of partial observations is a fundamental problem in various applied fields. In computer graphics, special attention has been given to the registration between two partial point clouds generated by scanning devices. State-of-the-art registration techniques still struggle when the overlap region between the two point clouds is small, and completely fail if there is no overlap between the scan pairs. In this article, we present a learning-based technique that alleviates this problem, and allows registration between point clouds, presented in arbitrary poses, and having little or even no overlap, a setting that has been referred to as tele-registration. Our technique is based on a novel neural network design that learns a prior of a class of shapes and can complete a partial shape. The key idea is combining the registration and completion tasks in a way that reinforces each other. In particular, we simultaneously train the registration network and completion network using two coupled flows, one that register-and-complete, and one that complete-and-register, and encourage the two flows to produce a consistent result. We show that, compared with each separate flow, this two-flow training leads to robust and reliable tele-registration, and hence to a better point cloud prediction that completes the registered scans. It is also worth mentioning that each of the components in our neural network outperforms state-of-the-art methods in both completion and registration. We further analyze our network with several ablation studies and demonstrate its performance on a large number of partial point clouds, both synthetic and real-world, that have only small or no overlap.

Laser scanners can easily acquire the geometric data of physical environments in the form of point clouds. Industrial 3D reconstruction processes generally recognize objects from point clouds, which should include both geometric and semantic data. However, the recognition process is often a bottleneck in 3D reconstruction because it is labor intensive and requires expertise in domain knowledge. To address this problem, various methods have been developed to recognize objects by retrieving their corresponding models from a database via input geometric queries. In recent years, geometric data conversion to images and view-based 3D shape retrieval applications have demonstrated high accuracies. Depth images that encode the depth values as pixel intensities are frequently used for view-based 3D shape retrieval. However, geometric data collected from objects are often incomplete owing to occlusions and line-of-sight limitations. Images generated by occluded point clouds lower the view-based 3D object retrieval performance owing to loss of information. In this paper, we propose a viewpoint and image-resolution estimation method for view-based 3D shape retrieval from point cloud queries. Further, automatic selection of viewpoint and image resolution are proposed using the data acquisition rate and density calculations from sampled viewpoints and image resolutions. The retrieval performances for images generated by the proposed method are investigated via experiments and compared for various datasets. Additionally, view-based 3D shape retrieval performance with a deep convolutional neural network was investigated using the proposed method.

3D human mesh recovery from point clouds is essential for various tasks, including AR/VR and human behavior understanding. Previous works in this field either require high-quality 3D human scans or sequential point clouds, which cannot be easily applied to low-quality 3D scans captured by consumer-level depth sensors. In this paper, we make the first attempt to reconstruct reliable 3D human shapes from single-frame partial point clouds. To achieve this, we propose an end-to-end learnable method, named VoteHMR. The core of VoteHMR is a novel occlusion-aware voting network that can first reliably produce visible joint-level features from the input partial point clouds, and then complete the joint-level features through the kinematic tree of the human skeleton. Compared with holistic features used by previous works, the joint-level features can not only effectively encode the human geometry information but also be robust to noisy inputs with self-occlusions and missing areas. By exploiting the rich complementary clues from the joint-level features and global features from the input point clouds, the proposed method encourages reliable and disentangled parameter predictions for statistical 3D human models, such as SMPL. The proposed method achieves state-of-the-art performances on two large-scale datasets, namely SURREAL and DFAUST. Furthermore, VoteHMR also demonstrates superior generalization ability on real-world datasets, such as Berkeley MHAD.

In the past few years, a significant progress has been achieved in Automated Construction Progress Monitoring, using a variety of Data Acquisition methods. In this paper, we propose a new method, which shall overcome certain deficiencies recognized in existing methods. The basic principles of our method are, first, to continuously acquire partial As-built point clouds by using multiple helmet-mounted scanners, which scan the indoor and outdoor scenes of locations where work is being done, and record point clouds, locations and time stamps. Second, merging partial, time stamped As-built point clouds to create a complete 4D as-built point cloud of construction in progress. Third, registering elements from the 4D as-built point cloud by using the existing 3D BIM geometry model as the reference model, and generate the 4D as-built BIM. The fourth step is the comparison of 4D as-built BIM and 4D as-designed BIM to identify the differences between both models. From the differences in elements, the time schedule deviations are identified and reported.

ABSTRACTHuman mesh reconstruction from point clouds has gained increasing attention in recent years. However, existing reconstruction pipelines predominantly focus on regressing human model parameters, which results in an indirect mapping between input observations and output meshes. In this letter, we introduce a point‐to‐vertex reconstruction method, which bypasses parameter spaces to reconstruct complete SMPL topology from partial point observations directly. Specifically, our framework employs a hierarchical approach to extract geometric information from the partial point cloud. The feature mapping process is realized via a transformer‐based architecture, which integrates parametric human model priors and employs hybrid position encoding. To further improve accuracy, the dual refinement module progressively refines the reconstruction process through sequential optimization in the coordinate and vertex‐level feature spaces. Experiments on SURREAL datasets demonstrate that our framework achieves state‐of‐the‐art performance, surpassing previous methods by 18.4% in MPVE (from 19.6 to 16.0 mm) and 10.2% in MPJPE (from 17.7 to 15.9 mm).

Collecting 3D point cloud data of buildings is important for many applications such as urban mapping, renovation, preservation, and energy simulation. However, laser-scanned point clouds are often difficult to analyze, visualize, and interpret due to incompletely scanned building facades caused by numerous sources of defects such as noise, occlusions, and moving objects. Several point cloud scene completion algorithms have been proposed in the literature, but they have been mostly applied to individual objects or small-scale indoor environments and not on large-scale scans of building facades. This paper introduces a method of performing point cloud scene completion of building facades using orthographic projection and generative adversarial inpainting methods. The point cloud is first converted into the 2D structured representation of depth and color images using an orthographic projection approach. Then, a data-driven 2D inpainting approach is used to predict the complete version of the scene, given the incomplete scene in the image domain. The 2D inpainting process is fully automated and uses a customized generative-adversarial network based on Pix2Pix that is trainable end-to-end. The inpainted 2D image is finally converted back into a 3D point cloud using depth remapping. The proposed method is compared against several baseline methods, including geometric methods such as Poisson reconstruction and hole-filling, as well as learning-based methods such as the point completion network (PCN) and TopNet. Performance evaluation is carried out based on the task of reconstructing real-world building facades from partial laser-scanned point clouds. Experimental results using the performance metrics of voxel precision, voxel recall, position error, and color error showed that the proposed method has the best performance overall.

Point clouds generated from real-world scanning are always incomplete and ununiformly distributed, which would cause structural losses in 3D shape representations. Therefore, a learning-based method is introduced in this paper to repair partial point clouds and restore complete shapes of target objects. First, we sample several local regions of inputs, encode their features and fuse them with independently extracted global features. Second, we establish a graph to connect all local features together, and then implement convolution with multi-head attention on the graph. Graph attention mechanism enables each local feature vector to search across the regions and selectively absorb other local features based on their relationships in high-dimensional feature space. Third, we design a coarse decoder to collect cross-region features from the graph and generate skeletons of complete point clouds, and a folding-based decoder is leveraged to generate final point clouds with high resolution. Our network is trained on six categories of objects from the ModelNet dataset, its performance is compared with several existing methods, the results show that our network is able to generate dense complete point cloud with the highest accuracy.