Abstract:Building upon the SAM2 vision foundation model for downstream segmentation, this study introduces Boundary Enhanced Depth (BED)-SAM2. The SAM2 Hiera encoder architecture is modified to directly encode monocular depth information from RGB images, thereby providing geometric cues that enhance object boundary delineation and facilitate the extraction of camouflaged object shapes. BED-SAM2 demonstrates competitive state-of-the-art performance across multiple salient and camouflaged object detection tasks with as few as five training epochs.
| Comments: | 9 pages, 5 figures, 5 tables. Presented as a poster at the CVPR 2026 Workshop on Computer Vision in the Wild (CVinW). Code available at this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| ACM classes: | I.4.6; I.4.8; I.2.10 |
| Cite as: | arXiv:2605.24893 [cs.CV] |
| (or arXiv:2605.24893v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.24893 arXiv-issued DOI via DataCite (pending registration) |
From: Tyler Rust [view email]
[v1]
Sun, 24 May 2026 06:41:18 UTC (4,761 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。