HPNet: Deep Primitive Segmentation Using Hybrid Representations
This addresses the challenge of 3D shape segmentation for computer vision and graphics applications, representing an incremental improvement over existing methods.
The paper tackles the problem of segmenting 3D point clouds into primitive patches by introducing HPNet, which uses hybrid representations and learned combination weights, resulting in significant performance gains on benchmark datasets ANSI and ABCParts.
This paper introduces HPNet, a novel deep-learning approach for segmenting a 3D shape represented as a point cloud into primitive patches. The key to deep primitive segmentation is learning a feature representation that can separate points of different primitives. Unlike utilizing a single feature representation, HPNet leverages hybrid representations that combine one learned semantic descriptor, two spectral descriptors derived from predicted geometric parameters, as well as an adjacency matrix that encodes sharp edges. Moreover, instead of merely concatenating the descriptors, HPNet optimally combines hybrid representations by learning combination weights. This weighting module builds on the entropy of input features. The output primitive segmentation is obtained from a mean-shift clustering module. Experimental results on benchmark datasets ANSI and ABCParts show that HPNet leads to significant performance gains from baseline approaches.