P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting

TL;DR

This paper introduces Point-to-Pixel Prompting, a method that leverages pre-trained 2D image models for 3D point cloud analysis by transforming point clouds into images, achieving high accuracy with minimal additional training.

Contribution

It proposes a novel Point-to-Pixel Prompting technique that enables effective transfer of pre-trained image models to 3D point cloud tasks with minimal parameter tuning.

Findings

Achieves 89.3% accuracy on ScanObjectNN's hardest setting.

Outperforms conventional point cloud models with fewer trainable parameters.

Demonstrates strong performance on ModelNet and ShapeNet datasets.

Abstract

Nowadays, pre-training big models on large-scale datasets has become a crucial topic in deep learning. The pre-trained models with high representation ability and transferability achieve a great success and dominate many downstream tasks in natural language processing and 2D vision. However, it is non-trivial to promote such a pretraining-tuning paradigm to the 3D vision, given the limited training data that are relatively inconvenient to collect. In this paper, we provide a new perspective of leveraging pre-trained 2D knowledge in 3D domain to tackle this problem, tuning pre-trained image models with the novel Point-to-Pixel prompting for point cloud analysis at a minor parameter cost. Following the principle of prompting engineering, we transform point clouds into colorful images with geometry-preserved projection and geometry-aware coloring to adapt to pre-trained image models, whose weights are kept frozen during the end-to-end optimization of point cloud analysis tasks. We conduct extensive experiments to demonstrate that cooperating with our proposed Point-to-Pixel Prompting, better pre-trained image model will lead to consistently better performance in 3D vision. Enjoying prosperous development from image pre-training field, our method attains 89.3% accuracy on the hardest setting of ScanObjectNN, surpassing conventional point cloud models with much fewer trainable parameters. Our framework also exhibits very competitive performance on ModelNet classification and ShapeNet Part Segmentation. Code is available at https://github.com/wangzy22/P2P.