Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions
european conference on computer vision, pp. 473-491, 2020.
Given the demonstrated effectiveness of Approximate Convex Decomposition in self-supervision, this opens the door to incorporating other shape decomposition methods from the classical geometry processing literature into deep neural network based models operating on point clouds
The problems of shape classification and part segmentation from 3D point clouds have garnered increasing attention in the last few years. But both of these problems suffer from relatively small training sets, creating the need for statistically efficient methods to learn 3D shape representations. In this work, we investigate the use of ...More
PPT (Upload PPT)