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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bahri, Ali, Yazdanpanah, Moslem, Dastani, Sahar, Noori, Mehrdad, Hakim, Gustavo Adolfo Vargas, Osowiechi, David, Beizaee, Farzad, Ayed, Ismail Ben, Desrosiers, Christian
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909623073636352
author Bahri, Ali
Yazdanpanah, Moslem
Dastani, Sahar
Noori, Mehrdad
Hakim, Gustavo Adolfo Vargas
Osowiechi, David
Beizaee, Farzad
Ayed, Ismail Ben
Desrosiers, Christian
author_facet Bahri, Ali
Yazdanpanah, Moslem
Dastani, Sahar
Noori, Mehrdad
Hakim, Gustavo Adolfo Vargas
Osowiechi, David
Beizaee, Farzad
Ayed, Ismail Ben
Desrosiers, Christian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19546
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
Bahri, Ali
Yazdanpanah, Moslem
Dastani, Sahar
Noori, Mehrdad
Hakim, Gustavo Adolfo Vargas
Osowiechi, David
Beizaee, Farzad
Ayed, Ismail Ben
Desrosiers, Christian
Computer Vision and Pattern Recognition
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.
title SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.19546