Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis

TL;DR

This paper introduces PointCMT, a cross-modal training strategy that leverages images to enhance 3D point cloud analysis, achieving state-of-the-art results without changing network architecture.

Contribution

It proposes a novel teacher-student framework for cross-modal knowledge distillation from images to point clouds, improving representation learning.

Findings

Significant accuracy improvements on ModelNet40 and ScanObjectNN datasets.

Effective elimination of distribution discrepancy between modalities.

State-of-the-art performance with existing backbones.

Abstract

Although recent point cloud analysis achieves impressive progress, the paradigm of representation learning from a single modality gradually meets its bottleneck. In this work, we take a step towards more discriminative 3D point cloud representation by fully taking advantages of images which inherently contain richer appearance information, e.g., texture, color, and shade. Specifically, this paper introduces a simple but effective point cloud cross-modality training (PointCMT) strategy, which utilizes view-images, i.e., rendered or projected 2D images of the 3D object, to boost point cloud analysis. In practice, to effectively acquire auxiliary knowledge from view images, we develop a teacher-student framework and formulate the cross modal learning as a knowledge distillation problem. PointCMT eliminates the distribution discrepancy between different modalities through novel feature and classifier enhancement criteria and avoids potential negative transfer effectively. Note that PointCMT effectively improves the point-only representation without architecture modification. Sufficient experiments verify significant gains on various datasets using appealing backbones, i.e., equipped with PointCMT, PointNet++ and PointMLP achieve state-of-the-art performance on two benchmarks, i.e., 94.4% and 86.7% accuracy on ModelNet40 and ScanObjectNN, respectively. Code will be made available at https://github.com/ZhanHeshen/PointCMT.