SPAC-Net: Rethinking Point Cloud Completion with Structural Prior

• URL: http://arxiv.org/abs/2411.15066v1
• Date: Fri, 22 Nov 2024 16:54:17 GMT
• Title: SPAC-Net: Rethinking Point Cloud Completion with Structural Prior
• Authors: Zizhao Wu, Jian Shi, Xuan Deng, Cheng Zhang, Genfu Yang, Ming Zeng, Yunhai Wang,
• Abstract summary: Point cloud completion aims to infer a complete shape from its partial observation. Many approaches utilize a pure encoderdecoder paradigm in which complete shape can be directly predicted by shape priors learned from partial scans. We propose a novel framework,termed SPAC-Net, that aims to rethink the completion task under the guidance of a new structural prior.
• Score: 17.334882020068697
• License:
• Abstract: Point cloud completion aims to infer a complete shape from its partial observation. Many approaches utilize a pure encoderdecoder paradigm in which complete shape can be directly predicted by shape priors learned from partial scans, however, these methods suffer from the loss of details inevitably due to the feature abstraction issues. In this paper, we propose a novel framework,termed SPAC-Net, that aims to rethink the completion task under the guidance of a new structural prior, we call it interface. Specifically, our method first investigates Marginal Detector (MAD) module to localize the interface, defined as the intersection between the known observation and the missing parts. Based on the interface, our method predicts the coarse shape by learning the displacement from the points in interface move to their corresponding position in missing parts. Furthermore, we devise an additional Structure Supplement(SSP) module before the upsampling stage to enhance the structural details of the coarse shape, enabling the upsampling module to focus more on the upsampling task. Extensive experiments have been conducted on several challenging benchmarks, and the results demonstrate that our method outperforms existing state-of-the-art approaches.

Related papers

• 3D Shape Completion on Unseen Categories:A Weakly-supervised Approach [61.76304400106871]
  We introduce a novel weakly-supervised framework to reconstruct the complete shapes from unseen categories. We first propose an end-to-end prior-assisted shape learning network that leverages data from the seen categories to infer a coarse shape. In addition, we propose a self-supervised shape refinement model to further refine the coarse shape.
  arXiv  Detail & Related papers  (2024-01-19T09:41:09Z)
• Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images [78.56114271538061]
  We introduce an explicit point-based human reconstruction framework called HaP. Our approach is featured by fully-explicit point cloud estimation, manipulation, generation, and refinement in the 3D geometric space. Our results may indicate a paradigm rollback to the fully-explicit and geometry-centric algorithm design.
  arXiv  Detail & Related papers  (2023-11-06T05:52:29Z)
• Shape Anchor Guided Holistic Indoor Scene Understanding [9.463220988312218]
  We propose a shape anchor guided learning strategy (AncLearn) for robust holistic indoor scene understanding. AncLearn generates anchors that dynamically fit instance surfaces to (i) unmix noise and target-related features for offering reliable proposals at the detection stage. We embed AncLearn into a reconstruction-from-detection learning system (AncRec) to generate high-quality semantic scene models.
  arXiv  Detail & Related papers  (2023-09-20T08:30:20Z)
• Point Cloud Completion Guided by Prior Knowledge via Causal Inference [19.935868881427226]
  We propose a novel approach to point cloud completion task called Point-PC. Point-PC uses a memory network to retrieve shape priors and designs a causal inference model to filter missing shape information. Experimental results on the ShapeNet-55, PCN, and KITTI datasets demonstrate that Point-PC outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-28T16:33:35Z)
• Prototype-Aware Heterogeneous Task for Point Cloud Completion [35.47134205562422]
  Point cloud completion aims at recovering original shape information from partial point clouds. Existing methods usually succeed in completion for standard shape, while failing to generate local details of point clouds for some non-standard shapes. In this work, we design an effective way to distinguish standard/non-standard shapes with the help of intra-class shape representation.
  arXiv  Detail & Related papers  (2022-09-05T02:43:06Z)
• Point Scene Understanding via Disentangled Instance Mesh Reconstruction [21.92736190195887]
  We propose aDisentangled Instance Mesh Reconstruction (DIMR) framework for effective point scene understanding. A segmentation-based backbone is applied to reduce false positive object proposals. We leverage a mesh-aware latent code space to disentangle the processes of shape completion and mesh generation.
  arXiv  Detail & Related papers  (2022-03-31T06:36:07Z)
• ME-PCN: Point Completion Conditioned on Mask Emptiness [50.414383063838336]
  Main-stream methods predict missing shapes by decoding a global feature learned from the input point cloud. We present ME-PCN, a point completion network that leverages emptiness' in 3D shape space.
  arXiv  Detail & Related papers  (2021-08-18T15:02:27Z)
• SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization [52.20602782690776]
  It is expensive and tedious to obtain large scale paired sparse-canned point sets for training from real scanned sparse data. We propose a self-supervised point cloud upsampling network, named SPU-Net, to capture the inherent upsampling patterns of points lying on the underlying object surface. We conduct various experiments on both synthetic and real-scanned datasets, and the results demonstrate that we achieve comparable performance to the state-of-the-art supervised methods.
  arXiv  Detail & Related papers  (2020-12-08T14:14:09Z)
• Skeleton-bridged Point Completion: From Global Inference to Local Adjustment [48.2757171993437]
  We propose a skeleton-bridged point completion network (SK-PCN) for shape completion. Given a partial scan, our method first predicts its 3D skeleton to obtain the global structure. We decouple the shape completion into structure estimation and surface reconstruction, which eases the learning difficulty.
  arXiv  Detail & Related papers  (2020-10-14T22:49:30Z)
• Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints [80.60538408386016]
  Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry. We propose an end-to-end trainable framework consisting of learnable modules for detection, feature extraction, matching and outlier rejection.
  arXiv  Detail & Related papers  (2020-07-29T21:41:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.