Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912348681273344 |
|---|---|
| author | Sun, Hongyu Ke, Qiuhong Cheng, Ming Wang, Yongcai Li, Deying Gou, Chenhui Cai, Jianfei |
| author_facet | Sun, Hongyu Ke, Qiuhong Cheng, Ming Wang, Yongcai Li, Deying Gou, Chenhui Cai, Jianfei |
| contents | This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training data (often inaccessible during online inference) and are limited to recognizing a fixed set of point cloud classes predefined during training, we explore a more practical and challenging scenario: adapting the model solely based on online test data to recognize both previously seen classes and novel, unseen classes at test time. To this end, we develop \textbf{Point-Cache}, a hierarchical cache model that captures essential clues of online test samples, particularly focusing on the global structure of point clouds and their local-part details. Point-Cache, which serves as a rich 3D knowledge base, is dynamically managed to prioritize the inclusion of high-quality samples. Designed as a plug-and-play module, our method can be flexibly integrated into large multimodal 3D models to support open-vocabulary point cloud recognition. Notably, our solution operates with efficiency comparable to zero-shot inference, as it is entirely training-free. Point-Cache demonstrates substantial gains across 8 challenging benchmarks and 4 representative large 3D models, highlighting its effectiveness. Code is available at https://github.com/auniquesun/Point-Cache. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12150 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis Sun, Hongyu Ke, Qiuhong Cheng, Ming Wang, Yongcai Li, Deying Gou, Chenhui Cai, Jianfei Computer Vision and Pattern Recognition This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training data (often inaccessible during online inference) and are limited to recognizing a fixed set of point cloud classes predefined during training, we explore a more practical and challenging scenario: adapting the model solely based on online test data to recognize both previously seen classes and novel, unseen classes at test time. To this end, we develop \textbf{Point-Cache}, a hierarchical cache model that captures essential clues of online test samples, particularly focusing on the global structure of point clouds and their local-part details. Point-Cache, which serves as a rich 3D knowledge base, is dynamically managed to prioritize the inclusion of high-quality samples. Designed as a plug-and-play module, our method can be flexibly integrated into large multimodal 3D models to support open-vocabulary point cloud recognition. Notably, our solution operates with efficiency comparable to zero-shot inference, as it is entirely training-free. Point-Cache demonstrates substantial gains across 8 challenging benchmarks and 4 representative large 3D models, highlighting its effectiveness. Code is available at https://github.com/auniquesun/Point-Cache. |
| title | Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12150 |