{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/smart-pc-skeletal-model-adaptation-for-robust","title":"SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds","arxiv_id":"2505.19546","date":"2025-05-26","proceeding":null,"authors":["Ali Bahri","Moslem Yazdanpanah","Sahar Dastani","Mehrdad Noori","Gustavo Adolfo Vargas Hakim","David Osowiechi","Farzad Beizaee","Ismail Ben Ayed","Christian Desrosiers"],"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.","url_abs":"https://arxiv.org/abs/2505.19546v1","url_pdf":"https://arxiv.org/pdf/2505.19546v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"smart-pc-skeletal-model-adaptation-for-robust","repo_url":"https://github.com/alibahri94/smart-pc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"point-cloud-classification","task_name":"Point Cloud Classification"}],"methods":[{"method_slug":"mate","method_name":"MATE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.19546","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}