Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
This addresses shape analysis challenges in 3D computer vision, offering incremental improvements over existing methods.
The paper tackles the problem of lacking shape descriptors for 3D point clouds by introducing a method to aggregate hypothetical curves, achieving state-of-the-art results including 94.2% classification accuracy on ModelNet40, 86.8 instance IoU on ShapeNetPart segmentation, and 0.11 cosine error on ModelNet40 normal estimation.
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 point-wise 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.