Point cloud completion via structured feature maps using a feedback network

SPC: Self-supervised 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.

Point cloud completion is a fundamental yet challenging task in 3D computer vision. While existing two-stage methods have made significant progress in shape completion, they often overlook the critical issue of point density imbalance, leading to geometrically unsound results with illusory completeness. In this paper, we propose BD-TNet, a novel balanced density-aware point cloud completion method that systematically addresses this overlooked problem. Specifically, we design a Partial-Connected U-Net structure that strategically reduces top-layer skip connections to rebalance the influence between explicit features of partial inputs and abstract features for predicting missing regions, thereby generating uniformly distributed seed points. Furthermore, we introduce EmbeddingTrie, a Trie-like hierarchical shape prior dictionary that enables adaptive multi-scale prior fusion through a divide-and-conquer strategy. To directly constrain local point density, we devise an Elastic Potential Energy Loss that models point clouds as spring systems, effectively guiding the optimization toward balanced distributions. We evaluate our method on PCN, ShapeNet-34/55, and KITTI datasets, and the results demonstrate that BD-TNet achieves state-of-the-art performance on Density-aware Chamfer Distance while producing visually superior, complete point clouds with balanced density distribution.

Point cloud completion recovers the complete point clouds from partial ones, providing numerous point cloud information for downstream tasks such as 3-D reconstruction and target detection. However, previous methods usually suffer from unstructured prediction of points in local regions and the discrete nature of the point cloud. To resolve these problems, we propose a point cloud completion network called TPDC. Representing the point cloud as a set of unordered features of points with local geometric information, we devise a Triangular Pyramid Extractor (TPE), using the simplest 3-D structure-a triangular pyramid-to convert the point cloud to a sequence of local geometric information. Our insight of revealing local geometric information in a complex environment is to design a Divide-and-Conquer Splitting Module in a Divide-and-Conquer Splitting Decoder (DCSD) to learn point-splitting patterns that can fit local regions the best. This module employs the Divide-and-Conquer approach to parallelly handle tasks related to fitting ground-truth values to base points and predicting the displacement of split points. This approach aims to make the base points align more closely with the ground-truth values while also forecasting the displacement of split points relative to the base points. Furthermore, we propose a more realistic and challenging benchmark, ShapeNetMask, with more random point cloud input, more complex random item occlusion, and more realistic random environmental perturbations. The results show that our method outperforms both widely used benchmarks as well as the new benchmark.

Point cloud completion aims to reconstruct the complete 3D shape from incomplete point clouds, and it is crucial for tasks such as 3D object detection and segmentation. Despite the continuous advances in point cloud analysis techniques, feature extraction methods are still confronted with apparent limitations. The sparse sampling of point clouds, used as inputs in most methods, often results in a certain loss of global structure information. Meanwhile, traditional local feature extraction methods usually struggle to capture the intricate geometric details. To overcome these drawbacks, we introduce PointCFormer, a transformer framework optimized for robust global retention and precise local detail capture in point cloud completion. This framework embraces several key advantages. First, we propose a relation-based local feature extraction method to perceive local delicate geometry characteristics. This approach establishes a fine-grained relationship metric between the target point and its k-nearest neighbors, quantifying each neighboring point's contribution to the target point's local features. Secondly, we introduce a progressive feature extractor that integrates our local feature perception method with self-attention. Starting with a denser sampling of points as input, it iteratively queries long-distance global dependencies and local neighborhood relationships. This extractor maintains enhanced global structure and refined local details, without generating substantial computational overhead. Additionally, we develop a correction module after generating point proxies in the latent space to reintroduce denser information from the input points, enhancing the representation capability of the point proxies. PointCFormer demonstrates state-of-the-art performance on several widely used benchmarks.

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.

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.

DcTr: Noise-robust point cloud completion by dual-channel transformer with cross-attention

Point cloud is often noisy and incomplete. Existing completion methods usually generate the complete shapes for missing regions of 3D objects based on the deterministic learning frameworks, which only predict a single reconstruction output. However, these methods ignore the ill-posed nature of the completion problem and do not fully account for multiple possible completion predictions corresponding to one incomplete input. To address this problem, we propose a flow-based network together with a multi-modal mapping strategy for 3D point cloud completion. Specially, an encoder is first introduced to encode the input point cloud data into a rich latent representation suitable for conditioning in all flow-layers. Then we design a conditional normalizing flow architecture to learn the exact distribution of the plausible completion shapes over the multi-modal latent space. Finally, in order to fully utilize additional shape information, we propose a tree-structured decoder to perform the inverse mapping for complete shape generation with high fidelity. The proposed flow network is trained using a single loss named the negative log-likelihood to capture the distribution variations between input and output, without complex reconstruction loss and adversarial loss. Extensive experiments on ShapeNet dataset, KITTI dataset and measured data demonstrate that our method outperforms the state-of-the-art point cloud completion methods through qualitative and quantitative analysis.

Reconstructing the incomplete point cloud into the complete and uniform one is a fundamental task in 3D point cloud processing. Some existing studies have explored the use of deep learning networks and representation learning to implement point cloud completion, but the completed shapes still appear unrealistic and non-uniform. To address this issue, we propose the idea of simulating the process of point cloud completion with local-to-global reasoning (LGR). Motivated to achieve the fine LGR, a novel mutual information (MI) maximization-based similarity operation is proposed, which realizes the reconstruction from incomplete point cloud to complete one by maximizing MI between global features and the prior features from the same 3D object. We adopt the Jenson-Shannon MI estimator to maximize the MI between global features and the priors in specific dimensions, which effectively increases the similarity of global and prior features. Compared with other existing works and similarity operations, the superior results indicate the efficacy of the proposed method and its advantages over existing ones in both the synthetic and real-world datasets. Our source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/wendydidi/MISO-PCN</uri> .

3D vehicle shape completion is a key task in urban environment reconstruction, since the available sensors and 3D scanning procedures (such as Mobile Laser Scanning) in an outdoor city scene cannot usually extract the entire car shapes, which can be necessary for specifying their geometric properties for further analysis or realistic visualization. In this paper, we propose a novel multi-view based 3D object point cloud completion technique. In contrast to existing approaches, our method operates on 2D images formed by projecting the point cloud from several virtual camera positions around the object of interest. Both color and geometrical information is considered during the process, generating dense textured point clouds, displaying realistic patterns in the missing regions from the partial inputs. We present both quantitative and qualitative tests on various synthetic and real laser scanned vehicle point clouds, which demonstrate that our method surpasses existing state-of-the-art approaches. By applying it to vehicles from the Shapenet dataset, our approach outperforms recent techniques in terms of Earth Mover’s Distance (EMD) and Chamfer Distance (CD) by 43.8% and 12.17%, respectively.

Completing point clouds using structural constraints for large-scale points absence in 3D building reconstruction

Estimating the complete 3D point cloud from an incomplete one lies at the core of many vision and robotics applications. Existing methods typically predict the complete point cloud based on the global shape representation extracted from the incomplete input. Although they could predict the overall shape of 3D objects, they are incapable of generating structure details of objects. Moreover, the partial input point sets obtained from range scans are often sparse, noisy and non-uniform, which largely hinder shape completion. In this paper, we propose an adaptive sampling and hierarchical folding network (ASHF-Net) for robust 3D point cloud completion. Our main contributions are two-fold. First, we propose a denoising auto-encoder with an adaptive sampling module, aiming at learning robust local region features that are insensitive to noise. Second, we propose a hierarchical folding decoder with the gated skip-attention and multi-resolution completion goal to effectively exploit the local structure details of partial inputs. We also design a KL regularization term to evenly distribute the generated points. Extensive experiments demonstrate that our method outperforms existing state-of-the-art methods on multiple 3D point cloud completion benchmarks.

Point cloud data in the real world is often affected by occlusion and light reflection, leading to incompleteness of the data. Large‐region missing point clouds will cause great deviations in downstream tasks. A dual feature fusion network (DFF‐Net) is proposed to improve the accuracy of the completion of a large missing region of the point cloud. First, a dual feature encoder is designed to extract and fuse the global and local features of the input point cloud. Subsequently, a decoder is used to directly generate a point cloud of missing region that retains local details. In order to make the generated point cloud more detailed, a loss function with multiple terms is employed to emphasise the distribution density and visual quality of the generated point cloud. A large number of experiments show that the authors’ DFF‐Net is better than the previous state‐of‐the‐art methods in the aspect of point cloud completion.

The point cloud is disordered and unstructured, and it is difficult to extract detailed features. The detailed part of the target shape is difficult to complete in the point cloud completion task. It proposes a point cloud completion network (BCA-Net) focusing on detail reconstruction, which can reduce noise and refine shapes. Specifically, it utilizes residual deformation architecture to avoid error points. The break and recombine refinement method is used to recover complete point cloud details. In addition, it proposes a bilateral confidence aggregation unit based on recurrent path aggregation to refine the coarse point cloud shape using multiple gating. Our experiments on the ShapeNet and Complete3D datasets demonstrate that our network performs better than other point cloud completion networks.