Hyperbolic Chamfer Distance for Point Cloud Completion and Beyond

• URL: http://arxiv.org/abs/2412.17951v1
• Date: Mon, 23 Dec 2024 20:04:07 GMT
• Title: Hyperbolic Chamfer Distance for Point Cloud Completion and Beyond
• Authors: Fangzhou Lin, Songlin Hou, Haotian Liu, Shang Gao, Kazunori D Yamada, Haichong K. Zhang, Ziming Zhang,
• Abstract summary: Chamfer Distance (CD) is vulnerable to the presence of outliers. Hyperbolic Chamfer Distance (HyperCD) is specifically designed for point cloud completion tasks.
• Score: 18.802664517825132
• License:
• Abstract: Chamfer Distance (CD) is widely used as a metric to quantify difference between two point clouds. In point cloud completion, Chamfer Distance (CD) is typically used as a loss function in deep learning frameworks. However, it is generally acknowledged within the field that Chamfer Distance (CD) is vulnerable to the presence of outliers, which can consequently lead to the convergence on suboptimal models. In divergence from the existing literature, which largely concentrates on resolving such concerns in the realm of Euclidean space, we put forth a notably uncomplicated yet potent metric specifically designed for point cloud completion tasks: {Hyperbolic Chamfer Distance (HyperCD)}. This metric conducts Chamfer Distance computations within the parameters of hyperbolic space. During the backpropagation process, HyperCD systematically allocates greater weight to matched point pairs exhibiting reduced Euclidean distances. This mechanism facilitates the preservation of accurate point pair matches while permitting the incremental adjustment of suboptimal matches, thereby contributing to enhanced point cloud completion outcomes. Moreover, measure the shape dissimilarity is not solely work for point cloud completion task, we further explore its applications in other generative related tasks, including single image reconstruction from point cloud, and upsampling. We demonstrate state-of-the-art performance on the point cloud completion benchmark datasets, PCN, ShapeNet-55, and ShapeNet-34, and show from visualization that HyperCD can significantly improve the surface smoothness, we also provide the provide experimental results beyond completion task.

Related papers

• Fully-Geometric Cross-Attention for Point Cloud Registration [51.865371511201765]
  Point cloud registration approaches often fail when the overlap between point clouds is low due to noisy point correspondences. This work introduces a novel cross-attention mechanism tailored for Transformer-based architectures that tackles this problem. We integrate the Gromov-Wasserstein distance into the cross-attention formulation to jointly compute distances between points across different point clouds. At the point level, we also devise a self-attention mechanism that aggregates the local geometric structure information into point features for fine matching.
  arXiv  Detail & Related papers  (2025-02-12T10:44:36Z)
• Efficient Point Clouds Upsampling via Flow Matching [16.948354780275388]
  Existing diffusion models struggle with inefficiencies as they map Gaussian noise to real point clouds. We propose PUFM, a flow matching approach to directly map sparse point clouds to their high-fidelity dense counterparts. Our method delivers superior upsampling quality but with fewer sampling steps.
  arXiv  Detail & Related papers  (2025-01-25T17:50:53Z)
• MBPU: A Plug-and-Play State Space Model for Point Cloud Upsamping with Fast Point Rendering [7.751874339957304]
  We introduce a network named MBPU built on top of the Mamba architecture, which performs well in long sequence modeling. We simultaneously predict the 3D position shift and 1D point-to-point distance as regression quantities to constrain the global features. It is noted that, by the merits of our fast point rendering, MBPU yields high-quality upsampled point clouds by effectively eliminating surface noise.
  arXiv  Detail & Related papers  (2024-10-21T12:13:43Z)
• Point Cloud Pre-training with Diffusion Models [62.12279263217138]
  We propose a novel pre-training method called Point cloud Diffusion pre-training (PointDif) PointDif achieves substantial improvement across various real-world datasets for diverse downstream tasks such as classification, segmentation and detection.
  arXiv  Detail & Related papers  (2023-11-25T08:10:05Z)
• Arbitrary point cloud upsampling via Dual Back-Projection Network [12.344557879284219]
  We propose a Dual Back-Projection network for point cloud upsampling (DBPnet) A Dual Back-Projection is formulated in an up-down-up manner for point cloud upsampling. Experimental results show that the proposed method achieves the lowest point set matching losses.
  arXiv  Detail & Related papers  (2023-07-18T06:11:09Z)
• Spotlights: Probing Shapes from Spherical Viewpoints [25.824284796437652]
  We propose a novel sampling model called Spotlights to represent a 3D shape as a compact 1D array of depth values. It simulates the configuration of cameras evenly distributed on a sphere, where each virtual camera casts light rays from its principal point through sample points on a small concentric spherical cap to probe for the possible intersections with the object surrounded by the sphere.
  arXiv  Detail & Related papers  (2022-05-25T08:23:18Z)
• Learning a Structured Latent Space for Unsupervised Point Cloud Completion [48.79411151132766]
  We propose a novel framework, which learns a unified and structured latent space that encoding both partial and complete point clouds. Our proposed method consistently outperforms state-of-the-art unsupervised methods on both synthetic ShapeNet and real-world KITTI, ScanNet, and Matterport3D datasets.
  arXiv  Detail & Related papers  (2022-03-29T13:58:44Z)
• A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion [69.32451612060214]
  Real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications. Most existing point cloud completion methods use Chamfer Distance (CD) loss for training. We propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion.
  arXiv  Detail & Related papers  (2021-12-07T06:59:06Z)
• Point Cloud Completion by Learning Shape Priors [74.80746431691938]
  shape priors include geometric information in both complete and partial point clouds. We design a feature alignment strategy to learn the shape prior from complete points, and a coarse to fine strategy to incorporate partial prior in the fine stage. We achieve state-of-the-art performances on the point cloud completion task.
  arXiv  Detail & Related papers  (2020-08-02T04:00:32Z)
• Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervision [68.35777836993212]
  We propose a Pseudo-LiDAR point cloud network to generate temporally and spatially high-quality point cloud sequences. By exploiting the scene flow between point clouds, the proposed network is able to learn a more accurate representation of the 3D spatial motion relationship.
  arXiv  Detail & Related papers  (2020-06-20T03:11:04Z)

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.