iSeg: Interactive 3D Segmentation via Interactive Attention
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_ | 1866913565148971008 |
|---|---|
| author | Lang, Itai Xu, Fei Decatur, Dale Babu, Sudarshan Hanocka, Rana |
| author_facet | Lang, Itai Xu, Fei Decatur, Dale Babu, Sudarshan Hanocka, Rana |
| contents | We present iSeg, a new interactive technique for segmenting 3D shapes. Previous works have focused mainly on leveraging pre-trained 2D foundation models for 3D segmentation based on text. However, text may be insufficient for accurately describing fine-grained spatial segmentations. Moreover, achieving a consistent 3D segmentation using a 2D model is highly challenging, since occluded areas of the same semantic region may not be visible together from any 2D view. Thus, we design a segmentation method conditioned on fine user clicks, which operates entirely in 3D. Our system accepts user clicks directly on the shape's surface, indicating the inclusion or exclusion of regions from the desired shape partition. To accommodate various click settings, we propose a novel interactive attention module capable of processing different numbers and types of clicks, enabling the training of a single unified interactive segmentation model. We apply iSeg to a myriad of shapes from different domains, demonstrating its versatility and faithfulness to the user's specifications. Our project page is at https://threedle.github.io/iSeg/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03219 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | iSeg: Interactive 3D Segmentation via Interactive Attention Lang, Itai Xu, Fei Decatur, Dale Babu, Sudarshan Hanocka, Rana Computer Vision and Pattern Recognition Graphics We present iSeg, a new interactive technique for segmenting 3D shapes. Previous works have focused mainly on leveraging pre-trained 2D foundation models for 3D segmentation based on text. However, text may be insufficient for accurately describing fine-grained spatial segmentations. Moreover, achieving a consistent 3D segmentation using a 2D model is highly challenging, since occluded areas of the same semantic region may not be visible together from any 2D view. Thus, we design a segmentation method conditioned on fine user clicks, which operates entirely in 3D. Our system accepts user clicks directly on the shape's surface, indicating the inclusion or exclusion of regions from the desired shape partition. To accommodate various click settings, we propose a novel interactive attention module capable of processing different numbers and types of clicks, enabling the training of a single unified interactive segmentation model. We apply iSeg to a myriad of shapes from different domains, demonstrating its versatility and faithfulness to the user's specifications. Our project page is at https://threedle.github.io/iSeg/. |
| title | iSeg: Interactive 3D Segmentation via Interactive Attention |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2404.03219 |