Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysis

TL;DR

This paper introduces a self-supervised pre-training method for 3D point cloud analysis using multi-view rendering, significantly enhancing model performance on various datasets and tasks.

Contribution

A novel self-supervised pre-training approach leveraging multi-view rendering and knowledge distillation for 3D point cloud networks.

Findings

Pre-training improves performance of PointNet, DGCNN, SR-UNet.

Synthetic data pre-training benefits high-level tasks.

Method outperforms state-of-the-art on multiple datasets.

Abstract

Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from point cloud data. Inspired by the success of deep learning in the image domain, we devise a novel pre-training technique for better model initialization by utilizing the multi-view rendering of the 3D data. Our pre-training is self-supervised by a local pixel/point level correspondence loss computed from perspective projection and a global image/point cloud level loss based on knowledge distillation, thus effectively improving upon popular point cloud networks, including PointNet, DGCNN and SR-UNet. These improved models outperform existing state-of-the-art methods on various datasets and downstream tasks. We also analyze the benefits of synthetic and real data for pre-training, and observe that pre-training on synthetic data is also useful for high-level downstream tasks. Code and pre-trained models are available at https://github.com/VinAIResearch/selfsup_pcd.