PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clicks
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_ | 1866918151550140416 |
|---|---|
| author | Zhang, Bojun Ye, Hangjian Zheng, Hao Huang, Jianzheng Lin, Zhengyu Guo, Zhenhong Zheng, Feng |
| author_facet | Zhang, Bojun Ye, Hangjian Zheng, Hao Huang, Jianzheng Lin, Zhengyu Guo, Zhenhong Zheng, Feng |
| contents | Fine-grained 3D part segmentation is crucial for enabling embodied AI systems to perform complex manipulation tasks, such as interacting with specific functional components of an object. However, existing interactive segmentation methods are largely confined to coarse, instance-level targets, while non-interactive approaches struggle with sparse, real-world scans and suffer from a severe lack of annotated data. To address these limitations, we introduce PinPoint3D, a novel interactive framework for fine-grained, multi-granularity 3D segmentation, capable of generating precise part-level masks from only a few user point clicks. A key component of our work is a new 3D data synthesis pipeline that we developed to create a large-scale, scene-level dataset with dense part annotations, overcoming a critical bottleneck that has hindered progress in this field. Through comprehensive experiments and user studies, we demonstrate that our method significantly outperforms existing approaches, achieving an average IoU of around 55.8% on each object part under first-click settings and surpassing 71.3% IoU with only a few additional clicks. Compared to current state-of-the-art baselines, PinPoint3D yields up to a 16% improvement in IoU and precision, highlighting its effectiveness on challenging, sparse point clouds with high efficiency. Our work represents a significant step towards more nuanced and precise machine perception and interaction in complex 3D environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_25970 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clicks Zhang, Bojun Ye, Hangjian Zheng, Hao Huang, Jianzheng Lin, Zhengyu Guo, Zhenhong Zheng, Feng Computer Vision and Pattern Recognition Fine-grained 3D part segmentation is crucial for enabling embodied AI systems to perform complex manipulation tasks, such as interacting with specific functional components of an object. However, existing interactive segmentation methods are largely confined to coarse, instance-level targets, while non-interactive approaches struggle with sparse, real-world scans and suffer from a severe lack of annotated data. To address these limitations, we introduce PinPoint3D, a novel interactive framework for fine-grained, multi-granularity 3D segmentation, capable of generating precise part-level masks from only a few user point clicks. A key component of our work is a new 3D data synthesis pipeline that we developed to create a large-scale, scene-level dataset with dense part annotations, overcoming a critical bottleneck that has hindered progress in this field. Through comprehensive experiments and user studies, we demonstrate that our method significantly outperforms existing approaches, achieving an average IoU of around 55.8% on each object part under first-click settings and surpassing 71.3% IoU with only a few additional clicks. Compared to current state-of-the-art baselines, PinPoint3D yields up to a 16% improvement in IoU and precision, highlighting its effectiveness on challenging, sparse point clouds with high efficiency. Our work represents a significant step towards more nuanced and precise machine perception and interaction in complex 3D environments. |
| title | PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clicks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.25970 |