Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

BED-SAM2: Boundary-Enhanced-Depth SAM2 via Monocular Geometric Priors

About

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.

Tyler Rust, Dara McNally, Kyle O'Donnell, Colin Kelly, Chandra Kambhamettu• 2026

Related benchmarks

TaskDatasetResultRank
Salient Object DetectionDUTS (test)
M (MAE)0.017
357
Camouflaged Object DetectionNC4K (test)
Sm0.912
89
Salient Object DetectionECSSD 1,000 images (test)
MAE0.017
68
Camouflaged Object DetectionCAMO 250 (test)
M (Mean Score)0.04
65
Salient Object DetectionHKU-IS 4,447 images (test)
MAE0.018
62
Salient Object DetectionPASCAL-S 850 images (test)
MAE0.041
61
Salient Object DetectionNJU2K
S-measure (Sα)92.5
46
Camouflaged Object DetectionCHAMELEON 76 (test)
Sm0.941
44
Salient Object DetectionDUT-OMRON 5168 images (test)
Sm89.8
29
Salient Object DetectionNLPR 300
Sm Score94.2
23
Showing 10 of 13 rows

Other info

Follow for update