Amodal SAM: A Unified Amodal Segmentation Framework with Generalization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910157562183680 |
|---|---|
| author | Zhang, Bo Tian, Zhuotao Tao, Xin Tang, Songlin Yu, Jun Pei, Wenjie |
| author_facet | Zhang, Bo Tian, Zhuotao Tao, Xin Tang, Songlin Yu, Jun Pei, Wenjie |
| contents | Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus on amodal segmentation within the training domain, these approaches often lack the generalization capacity to extend effectively to novel object categories and unseen contexts. This paper introduces Amodal SAM, a unified framework that leverages SAM (Segment Anything Model) for both amodal image and amodal video segmentation. Amodal SAM preserves the powerful generalization ability of SAM while extending its inherent capabilities to the amodal segmentation task. The improvements lie in three aspects: (1) a lightweight Spatial Completion Adapter that enables occluded region reconstruction, (2) a Target-Aware Occlusion Synthesis (TAOS) pipeline that addresses the scarcity of amodal annotations by generating diverse synthetic training data, and (3) novel learning objectives that enforce regional consistency and topological regularization. Extensive experiments demonstrate that Amodal SAM achieves state-of-the-art performance on standard benchmarks, while simultaneously exhibiting robust generalization to novel scenarios. We anticipate that this research will advance the field toward practical amodal segmentation systems capable of operating effectively in unconstrained real-world environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20748 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Amodal SAM: A Unified Amodal Segmentation Framework with Generalization Zhang, Bo Tian, Zhuotao Tao, Xin Tang, Songlin Yu, Jun Pei, Wenjie Computer Vision and Pattern Recognition I.4.6 Amodal segmentation is a challenging task that aims to predict the complete geometric shape of objects, including their occluded regions. Although existing methods primarily focus on amodal segmentation within the training domain, these approaches often lack the generalization capacity to extend effectively to novel object categories and unseen contexts. This paper introduces Amodal SAM, a unified framework that leverages SAM (Segment Anything Model) for both amodal image and amodal video segmentation. Amodal SAM preserves the powerful generalization ability of SAM while extending its inherent capabilities to the amodal segmentation task. The improvements lie in three aspects: (1) a lightweight Spatial Completion Adapter that enables occluded region reconstruction, (2) a Target-Aware Occlusion Synthesis (TAOS) pipeline that addresses the scarcity of amodal annotations by generating diverse synthetic training data, and (3) novel learning objectives that enforce regional consistency and topological regularization. Extensive experiments demonstrate that Amodal SAM achieves state-of-the-art performance on standard benchmarks, while simultaneously exhibiting robust generalization to novel scenarios. We anticipate that this research will advance the field toward practical amodal segmentation systems capable of operating effectively in unconstrained real-world environments. |
| title | Amodal SAM: A Unified Amodal Segmentation Framework with Generalization |
| topic | Computer Vision and Pattern Recognition I.4.6 |
| url | https://arxiv.org/abs/2604.20748 |