Papers › CamoSAM2: Motion-Appearance Induced Auto-Refining Prompts for Video Camouflaged Object...
CamoSAM2: Motion-Appearance Induced Auto-Refining Prompts for Video Camouflaged Object Detection
Xin Zhang, Keren Fu, Qijun Zhao
The Segment Anything Model 2 (SAM2), a prompt-guided video foundation model, has remarkably performed in video object segmentation, drawing significant attention in the community. Due to the high similarity between camouflaged objects and their surroundings, which makes them difficult to distinguish even by the human eye, the application of SAM2 for automated segmentation in real-world scenarios faces challenges in camouflage perception and reliable prompts generation. To address these issues, we propose CamoSAM2, a motion-appearance prompt inducer (MAPI) and refinement framework to automatically generate and refine prompts for SAM2, enabling high-quality automatic detection and segmentation in VCOD task. Initially, we introduce a prompt inducer that simultaneously integrates motion and appearance cues to detect camouflaged objects, delivering more accurate initial predictions than existing methods. Subsequently, we propose a video-based adaptive multi-prompts refinement (AMPR) strategy tailored for SAM2, aimed at mitigating prompt error in initial coarse masks and further producing good prompts. Specifically, we introduce a novel three-step process to generate reliable prompts by camouflaged object determination, pivotal prompting frame selection, and multi-prompts formation. Extensive experiments conducted on two benchmark datasets demonstrate that our proposed model, CamoSAM2, significantly outperforms existing state-of-the-art methods, achieving increases of 8.0% and 10.1% in mIoU metric. Additionally, our method achieves the fastest inference speed compared to current VCOD models.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Camouflaged Object Segmentation | MoCA-Mask | CamoSAM2 | MAE | 0.007 | #2 of 4 | Archive leaderboard | report |
| Camouflaged Object Segmentation | MoCA-Mask | CamoSAM2 | S-measure | 0.765 | #2 of 4 | Archive leaderboard | report |
| Camouflaged Object Segmentation | MoCA-Mask | CamoSAM2 | mDice | 0.62 | #2 of 4 | Archive leaderboard | report |
| Camouflaged Object Segmentation | MoCA-Mask | CamoSAM2 | mIoU | 0.542 | #2 of 4 | Archive leaderboard | report |
| Camouflaged Object Segmentation | MoCA-Mask | CamoSAM2 | weighted F-measure | 0.607 | #2 of 4 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections