APSNet: Attention Based Point Cloud Sampling

by   Yang Ye, et al.

Processing large point clouds is a challenging task. Therefore, the data is often downsampled to a smaller size such that it can be stored, transmitted and processed more efficiently without incurring significant performance degradation. Traditional task-agnostic sampling methods, such as farthest point sampling (FPS), do not consider downstream tasks when sampling point clouds, and thus non-informative points to the tasks are often sampled. This paper explores a task-oriented sampling for 3D point clouds, and aims to sample a subset of points that are tailored specifically to a downstream task of interest. Similar to FPS, we assume that point to be sampled next should depend heavily on the points that have already been sampled. We thus formulate point cloud sampling as a sequential generation process, and develop an attention-based point cloud sampling network (APSNet) to tackle this problem. At each time step, APSNet attends to all the points in a cloud by utilizing the history of previously sampled points, and samples the most informative one. Both supervised learning and knowledge distillation-based self-supervised learning of APSNet are proposed. Moreover, joint training of APSNet over multiple sample sizes is investigated, leading to a single APSNet that can generate arbitrary length of samples with prominent performances. Extensive experiments demonstrate the superior performance of APSNet against state-of-the-arts in various downstream tasks, including 3D point cloud classification, reconstruction, and registration.


page 2

page 19


AS-PD: An Arbitrary-Size Downsampling Framework for Point Clouds

Point cloud downsampling is a crucial pre-processing operation to downsa...

Learning to Sample

Processing large point clouds is a challenging task. Therefore, the data...

PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery

Point Cloud Sampling and Recovery (PCSR) is critical for massive real-ti...

Masked Discrimination for Self-Supervised Learning on Point Clouds

Masked autoencoding has achieved great success for self-supervised learn...

Self-Ordering Point Clouds

In this paper we address the task of finding representative subsets of p...

Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds

Sampling is a key operation in point-cloud task and acts to increase com...

Keypoint Autoencoders: Learning Interest Points of Semantics

Understanding point clouds is of great importance. Many previous methods...

Please sign up or login with your details

Forgot password? Click here to reset