Keypoint Autoencoders: Learning Interest Points of Semantics

TL;DR

This paper introduces Keypoint Autoencoders, an unsupervised method for detecting semantically meaningful keypoints in point clouds, improving downstream shape classification performance.

Contribution

It proposes a novel differentiable soft keypoint proposal mechanism and introduces metrics for semantic accuracy and richness.

Findings

Achieves competitive or superior performance on semantic metrics.

Effectively detects sparse, meaningful keypoints for shape classification.

Demonstrates the importance of semantic information in keypoint detection.

Abstract

Understanding point clouds is of great importance. Many previous methods focus on detecting salient keypoints to identity structures of point clouds. However, existing methods neglect the semantics of points selected, leading to poor performance on downstream tasks. In this paper, we propose Keypoint Autoencoder, an unsupervised learning method for detecting keypoints. We encourage selecting sparse semantic keypoints by enforcing the reconstruction from keypoints to the original point cloud. To make sparse keypoint selection differentiable, Soft Keypoint Proposal is adopted by calculating weighted averages among input points. A downstream task of classifying shape with sparse keypoints is conducted to demonstrate the distinctiveness of our selected keypoints. Semantic Accuracy and Semantic Richness are proposed and our method gives competitive or even better performance than state of the arts on these two metrics.