PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation

TL;DR

PointVST introduces a self-supervised pre-training method for 3D point clouds by translating them into 2D images, significantly improving downstream task performance and domain transfer capabilities.

Contribution

It proposes a novel cross-modal translation pretext task for 3D point cloud pre-training, bridging the gap between 3D and 2D representations.

Findings

Outperforms state-of-the-art methods on various tasks

Demonstrates strong domain transfer ability

Shows consistent performance improvements

Abstract

The past few years have witnessed the great success and prevalence of self-supervised representation learning within the language and 2D vision communities. However, such advancements have not been fully migrated to the field of 3D point cloud learning. Different from existing pre-training paradigms designed for deep point cloud feature extractors that fall into the scope of generative modeling or contrastive learning, this paper proposes a translative pre-training framework, namely PointVST, driven by a novel self-supervised pretext task of cross-modal translation from 3D point clouds to their corresponding diverse forms of 2D rendered images. More specifically, we begin with deducing view-conditioned point-wise embeddings through the insertion of the viewpoint indicator, and then adaptively aggregate a view-specific global codeword, which can be further fed into subsequent 2D convolutional translation heads for image generation. Extensive experimental evaluations on various downstream task scenarios demonstrate that our PointVST shows consistent and prominent performance superiority over current state-of-the-art approaches as well as satisfactory domain transfer capability. Our code will be publicly available at https://github.com/keeganhk/PointVST.