SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds

TL;DR

SMART-PC introduces a skeleton-based, real-time test-time training framework for 3D point cloud classification that enhances robustness to corruptions without expensive backpropagation, achieving high efficiency and state-of-the-art accuracy.

Contribution

It proposes a novel skeleton-based framework that predicts skeletal representations during pre-training, enabling efficient test-time adaptation by updating only BatchNorm statistics.

Findings

Outperforms existing methods on benchmark datasets.

Achieves real-time adaptation with high frame rates.

Maintains superior classification accuracy under corruptions.

Abstract

Test-Time Training (TTT) has emerged as a promising solution to address distribution shifts in 3D point cloud classification. However, existing methods often rely on computationally expensive backpropagation during adaptation, limiting their applicability in real-world, time-sensitive scenarios. In this paper, we introduce SMART-PC, a skeleton-based framework that enhances resilience to corruptions by leveraging the geometric structure of 3D point clouds. During pre-training, our method predicts skeletal representations, enabling the model to extract robust and meaningful geometric features that are less sensitive to corruptions, thereby improving adaptability to test-time distribution shifts. Unlike prior approaches, SMART-PC achieves real-time adaptation by eliminating backpropagation and updating only BatchNorm statistics, resulting in a lightweight and efficient framework capable of achieving high frame-per-second rates while maintaining superior classification performance. Extensive experiments on benchmark datasets, including ModelNet40-C, ShapeNet-C, and ScanObjectNN-C, demonstrate that SMART-PC achieves state-of-the-art results, outperforming existing methods such as MATE in terms of both accuracy and computational efficiency. The implementation is available at: https://github.com/AliBahri94/SMART-PC.