3x2: 3D Object Part Segmentation by 2D Semantic Correspondences
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917721480888320 |
|---|---|
| author | Thai, Anh Wang, Weiyao Tang, Hao Stojanov, Stefan Feiszli, Matt Rehg, James M. |
| author_facet | Thai, Anh Wang, Weiyao Tang, Hao Stojanov, Stefan Feiszli, Matt Rehg, James M. |
| contents | 3D object part segmentation is essential in computer vision applications. While substantial progress has been made in 2D object part segmentation, the 3D counterpart has received less attention, in part due to the scarcity of annotated 3D datasets, which are expensive to collect. In this work, we propose to leverage a few annotated 3D shapes or richly annotated 2D datasets to perform 3D object part segmentation. We present our novel approach, termed 3-By-2 that achieves SOTA performance on different benchmarks with various granularity levels. By using features from pretrained foundation models and exploiting semantic and geometric correspondences, we are able to overcome the challenges of limited 3D annotations. Our approach leverages available 2D labels, enabling effective 3D object part segmentation. Our method 3-By-2 can accommodate various part taxonomies and granularities, demonstrating interesting part label transfer ability across different object categories. Project website: \url{https://ngailapdi.github.io/projects/3by2/}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_09648 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 3x2: 3D Object Part Segmentation by 2D Semantic Correspondences Thai, Anh Wang, Weiyao Tang, Hao Stojanov, Stefan Feiszli, Matt Rehg, James M. Computer Vision and Pattern Recognition 3D object part segmentation is essential in computer vision applications. While substantial progress has been made in 2D object part segmentation, the 3D counterpart has received less attention, in part due to the scarcity of annotated 3D datasets, which are expensive to collect. In this work, we propose to leverage a few annotated 3D shapes or richly annotated 2D datasets to perform 3D object part segmentation. We present our novel approach, termed 3-By-2 that achieves SOTA performance on different benchmarks with various granularity levels. By using features from pretrained foundation models and exploiting semantic and geometric correspondences, we are able to overcome the challenges of limited 3D annotations. Our approach leverages available 2D labels, enabling effective 3D object part segmentation. Our method 3-By-2 can accommodate various part taxonomies and granularities, demonstrating interesting part label transfer ability across different object categories. Project website: \url{https://ngailapdi.github.io/projects/3by2/}. |
| title | 3x2: 3D Object Part Segmentation by 2D Semantic Correspondences |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.09648 |