Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912290974990336 |
|---|---|
| author | Lee, Jae Joong Benes, Bedrich Yeh, Raymond A. |
| author_facet | Lee, Jae Joong Benes, Bedrich Yeh, Raymond A. |
| contents | Amodal segmentation aims to predict segmentation masks for both the visible and occluded regions of an object. Most existing works formulate this as a supervised learning problem, requiring manually annotated amodal masks or synthetic training data. Consequently, their performance depends on the quality of the datasets, which often lack diversity and scale. This work introduces a tuning-free approach that repurposes pretrained diffusion-based inpainting models for amodal segmentation. Our approach is motivated by the "occlusion-free bias" of inpainting models, i.e., the inpainted objects tend to be complete objects without occlusions. Specifically, we reconstruct the occluded regions of an object via inpainting and then apply segmentation, all without additional training or fine-tuning. Experiments on five datasets demonstrate the generalizability and robustness of our approach. On average, our approach achieves 5.3% more accurate masks over the state-of-the-art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18947 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting Models Lee, Jae Joong Benes, Bedrich Yeh, Raymond A. Computer Vision and Pattern Recognition Amodal segmentation aims to predict segmentation masks for both the visible and occluded regions of an object. Most existing works formulate this as a supervised learning problem, requiring manually annotated amodal masks or synthetic training data. Consequently, their performance depends on the quality of the datasets, which often lack diversity and scale. This work introduces a tuning-free approach that repurposes pretrained diffusion-based inpainting models for amodal segmentation. Our approach is motivated by the "occlusion-free bias" of inpainting models, i.e., the inpainted objects tend to be complete objects without occlusions. Specifically, we reconstruct the occluded regions of an object via inpainting and then apply segmentation, all without additional training or fine-tuning. Experiments on five datasets demonstrate the generalizability and robustness of our approach. On average, our approach achieves 5.3% more accurate masks over the state-of-the-art. |
| title | Tuning-Free Amodal Segmentation via the Occlusion-Free Bias of Inpainting Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18947 |