Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis

Discrete point cloud objects lack sufficient shape descriptors of 3D geometries. In this paper, we present a novel method for aggregating hypothetical curves in point clouds. Sequences of connected points (curves) are initially grouped by taking guided walks in the point clouds, and then subsequentl...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiang, Tiange, Zhang, Chaoyi, Song, Yang, Yu, Jianhui, Cai, Weidong
Format: Conference Proceeding
Language:English
Subjects:
Analytical models
Codes
Computer vision
Geometry
grouping and shape
Point cloud compression
Recognition and classification
Segmentation
Shape
Three-dimensional displays
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Discrete point cloud objects lack sufficient shape descriptors of 3D geometries. In this paper, we present a novel method for aggregating hypothetical curves in point clouds. Sequences of connected points (curves) are initially grouped by taking guided walks in the point clouds, and then subsequently aggregated back to augment their pointwise features. We provide an effective implementation of the proposed aggregation strategy including a novel curve grouping operator followed by a curve aggregation operator. Our method was benchmarked on several point cloud analysis tasks where we achieved the state-of-the-art classification accuracy of 94.2% on the ModelNet40 classification task, instance IoU of 86.8% on the ShapeNetPart segmentation task and cosine error of 0.11 on the ModelNet40 normal estimation task. Our project page with source code is available at: https://curvenet.github.io/.
ISSN:2380-7504
DOI:10.1109/ICCV48922.2021.00095