Keypoint Autoencoders: Learning Interest Points of Semantics
This work addresses the issue of poor downstream task performance in point cloud analysis due to neglected semantics in keypoint selection, offering an incremental improvement for researchers in 3D vision.
The paper tackles the problem of detecting semantic keypoints in point clouds by proposing Keypoint Autoencoder, an unsupervised method that enforces reconstruction from sparse keypoints, resulting in competitive or better performance on Semantic Accuracy and Semantic Richness metrics compared to state-of-the-art methods.
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.