Unleash the Potential of 3D Point Cloud Modeling with A Calibrated Local Geometry-driven Distance Metric

• URL: http://arxiv.org/abs/2306.00552v1
• Date: Thu, 1 Jun 2023 11:16:20 GMT
• Title: Unleash the Potential of 3D Point Cloud Modeling with A Calibrated Local Geometry-driven Distance Metric
• Authors: Siyu Ren and Junhui Hou
• Abstract summary: We propose a novel distance metric called Calibrated Local Geometry Distance (CLGD) CLGD computes the difference between the underlying 3D surfaces calibrated and induced by a set of reference points. As a generic metric, CLGD has the potential to advance 3D point cloud modeling.
• Score: 62.365983810610985
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantifying the dissimilarity between two unstructured 3D point clouds is a challenging task, with existing metrics often relying on measuring the distance between corresponding points that can be either inefficient or ineffective. In this paper, we propose a novel distance metric called Calibrated Local Geometry Distance (CLGD), which computes the difference between the underlying 3D surfaces calibrated and induced by a set of reference points. By associating each reference point with two given point clouds through computing its directional distances to them, the difference in directional distances of an identical reference point characterizes the geometric difference between a typical local region of the two point clouds. Finally, CLGD is obtained by averaging the directional distance differences of all reference points. We evaluate CLGD on various optimization and unsupervised learning-based tasks, including shape reconstruction, rigid registration, scene flow estimation, and feature representation. Extensive experiments show that CLGD achieves significantly higher accuracy under all tasks in a memory and computationally efficient manner, compared with existing metrics. As a generic metric, CLGD has the potential to advance 3D point cloud modeling. The source code is publicly available at https://github.com/rsy6318/CLGD.

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)
• PDM-SSD: Single-Stage Three-Dimensional Object Detector With Point Dilation [7.113034810057012]
  Current Point-based detectors can only learn from the provided points. We present a novel Point Dilation Mechanism for single-stage 3D detection (PDM-SSD) PDM-SSD achieves state-of-the-art results for multi-class detection among single-modal methods with an inference speed of 68 frames.
  arXiv  Detail & Related papers  (2025-02-10T12:41:13Z)
• Measuring the Discrepancy between 3D Geometric Models using Directional Distance Fields [98.15456815880911]
  We propose DirDist, an efficient, effective, robust, and differentiable distance metric for 3D geometry data. As a generic distance metric, DirDist has the potential to advance the field of 3D geometric modeling.
  arXiv  Detail & Related papers  (2024-01-18T05:31:53Z)
• PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Prediction [72.75478398447396]
  We propose a cylindrical tri-perspective view to represent point clouds effectively and comprehensively. Considering the distance distribution of LiDAR point clouds, we construct the tri-perspective view in the cylindrical coordinate system. We employ spatial group pooling to maintain structural details during projection and adopt 2D backbones to efficiently process each TPV plane.
  arXiv  Detail & Related papers  (2023-08-31T17:57:17Z)
• Quadric Representations for LiDAR Odometry, Mapping and Localization [93.24140840537912]
  Current LiDAR odometry, mapping and localization methods leverage point-wise representations of 3D scenes. We propose a novel method of describing scenes using quadric surfaces, which are far more compact representations of 3D objects. Our method maintains low latency and memory utility while achieving competitive, and even superior, accuracy.
  arXiv  Detail & Related papers  (2023-04-27T13:52:01Z)
• Soft Expectation and Deep Maximization for Image Feature Detection [68.8204255655161]
  We propose SEDM, an iterative semi-supervised learning process that flips the question and first looks for repeatable 3D points, then trains a detector to localize them in image space. Our results show that this new model trained using SEDM is able to better localize the underlying 3D points in a scene.
  arXiv  Detail & Related papers  (2021-04-21T00:35:32Z)
• Point-set Distances for Learning Representations of 3D Point Clouds [21.860204082926415]
  We propose to use a variant of the Wasserstein distance, named the sliced Wasserstein distance, for learning representations of 3D point clouds. Experiments show that the sliced Wasserstein distance allows the neural network to learn a more efficient representation compared to the Chamfer discrepancy.
  arXiv  Detail & Related papers  (2021-02-08T06:09:13Z)

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.