SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
This addresses the challenge of real-time, robust point cloud classification for applications like robotics or autonomous systems, though it is incremental as it builds on existing test-time training methods.
The paper tackles the problem of distribution shifts in 3D point cloud classification by introducing SMART-PC, a skeleton-based framework that achieves real-time adaptation without backpropagation, resulting in state-of-the-art accuracy and high computational efficiency on benchmark datasets.
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.