BED-SAM2: Boundary-Enhanced-Depth SAM2 via Monocular Geometric Priors
For researchers in segmentation and object detection, this work offers a lightweight enhancement to SAM2 that improves boundary delineation with minimal training.
BED-SAM2 modifies the SAM2 encoder to incorporate monocular depth cues, achieving competitive SOTA on salient and camouflaged object detection in as few as five training epochs.
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.