Self-Ordering Point Clouds
This addresses the challenge of ordering point clouds without hard-to-obtain labels, which is incremental as it builds on prior supervised approaches.
The paper tackles the problem of finding representative subsets of points in 3D point clouds by introducing self-supervised point-wise ordering, achieving superior performance compared to supervised methods on multiple datasets and tasks, including zero-shot ordering on unseen categories.
In this paper we address the task of finding representative subsets of points in a 3D point cloud by means of a point-wise ordering. Only a few works have tried to address this challenging vision problem, all with the help of hard to obtain point and cloud labels. Different from these works, we introduce the task of point-wise ordering in 3D point clouds through self-supervision, which we call self-ordering. We further contribute the first end-to-end trainable network that learns a point-wise ordering in a self-supervised fashion. It utilizes a novel differentiable point scoring-sorting strategy and it constructs an hierarchical contrastive scheme to obtain self-supervision signals. We extensively ablate the method and show its scalability and superior performance even compared to supervised ordering methods on multiple datasets and tasks including zero-shot ordering of point clouds from unseen categories.