CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation

TL;DR

CloudFixer introduces a novel test-time adaptation method for 3D point clouds using a diffusion-guided geometric transformation, significantly improving robustness against noise and distribution shifts while maintaining computational efficiency.

Contribution

It presents a tailored TTA approach for 3D point clouds that leverages a pre-trained diffusion model and geometric transformations, addressing computational and property-specific challenges.

Findings

Outperforms existing TTA baselines in handling corruptions and shifts

Enhances robustness of 3D recognition models in real-world scenarios

Achieves computational efficiency by avoiding backpropagation through the diffusion model

Abstract

3D point clouds captured from real-world sensors frequently encompass noisy points due to various obstacles, such as occlusion, limited resolution, and variations in scale. These challenges hinder the deployment of pre-trained point cloud recognition models trained on clean point clouds, leading to significant performance degradation. While test-time adaptation (TTA) strategies have shown promising results on this issue in the 2D domain, their application to 3D point clouds remains under-explored. Among TTA methods, an input adaptation approach, which directly converts test instances to the source domain using a pre-trained diffusion model, has been proposed in the 2D domain. Despite its robust TTA performance in practical situations, naively adopting this into the 3D domain may be suboptimal due to the neglect of inherent properties of point clouds, and its prohibitive computational cost. Motivated by these limitations, we propose CloudFixer, a test-time input adaptation method tailored for 3D point clouds, employing a pre-trained diffusion model. Specifically, CloudFixer optimizes geometric transformation parameters with carefully designed objectives that leverage the geometric properties of point clouds. We also substantially improve computational efficiency by avoiding backpropagation through the diffusion model and a prohibitive generation process. Furthermore, we propose an online model adaptation strategy by aligning the original model prediction with that of the adapted input. Extensive experiments showcase the superiority of CloudFixer over various TTA baselines, excelling in handling common corruptions and natural distribution shifts across diverse real-world scenarios. Our code is available at https://github.com/shimazing/CloudFixer