用骨骼结构提升点云分类抗干扰能力，实时适配无需反向传播。
SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
- 基于点云几何骨架预训练，提取抗噪特征
- 仅更新BatchNorm统计量，实测达百帧以上速率
- 适合部署在实时性要求高的3D识别场景
测试时训练（TTT）为应对3D点云分类中的分布偏移提供了有前景的解决方案。然而，现有方法常依赖计算开销大的反向传播进行适应，限制了其在真实时间敏感场景的应用。本文提出SMART-PC，一种基于骨骼结构的框架，通过利用点云几何结构增强对噪声的鲁棒性。预训练阶段，模型预测骨骼表示，从而提取更鲁棒、有意义的几何特征，提升对测试时分布变化的适应能力。与以往方法不同，SMART-PC通过去除反向传播，仅更新BatchNorm统计量，实现轻量高效，可在保持优异分类性能的同时达到高帧率（>100 FPS）。在ModelNet40-C、ShapeNet-C和ScanObjectNN-C等基准数据集上的大量实验表明，SMART-PC在准确率与计算效率上均优于MATE等现有方法。代码已公开：https://github.com/AliBahri94/SMART-PC。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。