Prototype-Aware Heterogeneous Task for Point Cloud Completion

• URL: http://arxiv.org/abs/2209.01733v1
• Date: Mon, 5 Sep 2022 02:43:06 GMT
• Title: Prototype-Aware Heterogeneous Task for Point Cloud Completion
• Authors: Junshu Tang, Jiachen Xu, Jingyu Gong, Haichuan Song, Yuan Xie, Lizhuang Ma
• Abstract summary: 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.
• Score: 35.47134205562422
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Point cloud completion, which aims at recovering original shape information from partial point clouds, has attracted attention on 3D vision community. Existing methods usually succeed in completion for standard shape, while failing to generate local details of point clouds for some non-standard shapes. To achieve desirable local details, guidance from global shape information is of critical importance. In this work, we design an effective way to distinguish standard/non-standard shapes with the help of intra-class shape prototypical representation, which can be calculated by the proposed supervised shape clustering pretext task, resulting in a heterogeneous component w.r.t completion network. The representative prototype, defined as feature centroid of shape categories, can provide global shape guidance, which is referred to as soft-perceptual prior, to inject into downstream completion network by the desired selective perceptual feature fusion module in a multi-scale manner. Moreover, for effective training, we consider difficulty-based sampling strategy to encourage the network to pay more attention to some partial point clouds with fewer geometric information. Experimental results show that our method outperforms other state-of-the-art methods and has strong ability on completing complex geometric shapes.

Related papers

• Unsupervised Non-Rigid Point Cloud Matching through Large Vision Models [1.3030624795284795]
  We propose a learning-based framework for non-rigid point cloud matching. Key insight is to incorporate semantic features derived from large vision models (LVMs) Our framework effectively leverages the structural information contained in the semantic features to address ambiguities arise from self-similarities among local geometries.
  arXiv  Detail & Related papers  (2024-08-16T07:02:19Z)
• 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)
• Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching [15.050801537501462]
  We introduce a self-supervised multimodal learning strategy that combines mesh-based functional map regularisation with a contrastive loss that couples mesh and point cloud data. Our shape matching approach allows to obtain intramodal correspondences for triangle meshes, complete point clouds, and partially observed point clouds. We demonstrate that our method achieves state-of-the-art results on several challenging benchmark datasets.
  arXiv  Detail & Related papers  (2023-03-20T09:47:02Z)
• SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation [50.53931728235875]
  We present SP-GAN, a new unsupervised sphere-guided generative model for direct synthesis of 3D shapes in the form of point clouds. Compared with existing models, SP-GAN is able to synthesize diverse and high-quality shapes with fine details.
  arXiv  Detail & Related papers  (2021-08-10T06:49:45Z)
• Point Discriminative Learning for Unsupervised Representation Learning on 3D Point Clouds [54.31515001741987]
  We propose a point discriminative learning method for unsupervised representation learning on 3D point clouds. We achieve this by imposing a novel point discrimination loss on the middle level and global level point features. Our method learns powerful representations and achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-08-04T15:11:48Z)
• Point Cloud Completion by Skip-attention Network with Hierarchical Folding [61.59710288271434]
  We propose Skip-Attention Network (SA-Net) for 3D point cloud completion. First, we propose a skip-attention mechanism to effectively exploit the local structure details of incomplete point clouds. Second, in order to fully utilize the selected geometric information encoded by skip-attention mechanism at different resolutions, we propose a novel structure-preserving decoder.
  arXiv  Detail & Related papers  (2020-05-08T06:23:51Z)
• Shape-Oriented Convolution Neural Network for Point Cloud Analysis [59.405388577930616]
  Point cloud is a principal data structure adopted for 3D geometric information encoding. Shape-oriented message passing scheme dubbed ShapeConv is proposed to focus on the representation learning of the underlying shape formed by each local neighboring point.
  arXiv  Detail & Related papers  (2020-04-20T16:11:51Z)
• Cascaded Refinement Network for Point Cloud Completion [74.80746431691938]
  We propose a cascaded refinement network together with a coarse-to-fine strategy to synthesize the detailed object shapes. Considering the local details of partial input with the global shape information together, we can preserve the existing details in the incomplete point set. We also design a patch discriminator that guarantees every local area has the same pattern with the ground truth to learn the complicated point distribution.
  arXiv  Detail & Related papers  (2020-04-07T13:03:29Z)
• SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds [96.51884187479585]
  We propose a novel 3D shape signature to explore the shape information from point clouds. By incorporating operations of symmetry, convex hull and chebyshev fitting, the proposed shape sig-nature is not only compact and effective but also robust to the noise. Experiments show that the proposed method performs remarkably better than existing methods on two large-scale datasets.
  arXiv  Detail & Related papers  (2020-04-06T16:01:41Z)

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.