MirrorSAM2: Segment Mirror in Videos with Depth Perception
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912598576857088 |
|---|---|
| author | Xu, Mingchen Lai, Yukun Ji, Ze Wu, Jing |
| author_facet | Xu, Mingchen Lai, Yukun Ji, Ze Wu, Jing |
| contents | This paper presents MirrorSAM2, the first framework that adapts Segment Anything Model 2 (SAM2) to the task of RGB-D video mirror segmentation. MirrorSAM2 addresses key challenges in mirror detection, such as reflection ambiguity and texture confusion, by introducing four tailored modules: a Depth Warping Module for RGB and depth alignment, a Depth-guided Multi-Scale Point Prompt Generator for automatic prompt generation, a Frequency Detail Attention Fusion Module to enhance structural boundaries, and a Mirror Mask Decoder with a learnable mirror token for refined segmentation. By fully leveraging the complementarity between RGB and depth, MirrorSAM2 extends SAM2's capabilities to the prompt-free setting. To our knowledge, this is the first work to enable SAM2 for automatic video mirror segmentation. Experiments on the VMD and DVMD benchmark demonstrate that MirrorSAM2 achieves SOTA performance, even under challenging conditions such as small mirrors, weak boundaries, and strong reflections. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17220 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MirrorSAM2: Segment Mirror in Videos with Depth Perception Xu, Mingchen Lai, Yukun Ji, Ze Wu, Jing Computer Vision and Pattern Recognition This paper presents MirrorSAM2, the first framework that adapts Segment Anything Model 2 (SAM2) to the task of RGB-D video mirror segmentation. MirrorSAM2 addresses key challenges in mirror detection, such as reflection ambiguity and texture confusion, by introducing four tailored modules: a Depth Warping Module for RGB and depth alignment, a Depth-guided Multi-Scale Point Prompt Generator for automatic prompt generation, a Frequency Detail Attention Fusion Module to enhance structural boundaries, and a Mirror Mask Decoder with a learnable mirror token for refined segmentation. By fully leveraging the complementarity between RGB and depth, MirrorSAM2 extends SAM2's capabilities to the prompt-free setting. To our knowledge, this is the first work to enable SAM2 for automatic video mirror segmentation. Experiments on the VMD and DVMD benchmark demonstrate that MirrorSAM2 achieves SOTA performance, even under challenging conditions such as small mirrors, weak boundaries, and strong reflections. |
| title | MirrorSAM2: Segment Mirror in Videos with Depth Perception |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.17220 |