Bi-CamoDiffusion: A Boundary-informed Diffusion Approach for Camouflaged Object Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912965747277824 |
|---|---|
| author | Suarez, Patricia L. Ramos, Leo Thomas Sappa, Angel D. |
| author_facet | Suarez, Patricia L. Ramos, Leo Thomas Sappa, Angel D. |
| contents | Bi-CamoDiffusion is introduced, an evolution of the CamoDiffusion framework for camouflaged object detection. It integrates edge priors into early-stage embeddings via a parameter-free injection process, which enhances boundary sharpness and prevents structural ambiguity. This is governed by a unified optimization objective that balances spatial accuracy, structural constraints, and uncertainty supervision, allowing the model to capture of both the object's global context and its intricate boundary transitions. Evaluations across the CAMO, COD10K, and NC4K benchmarks show that Bi-CamoDiffusion surpasses the baseline, delivering sharper delineation of thin structures and protrusions while also minimizing false positives. Also, our model consistently outperforms existing state-of-the-art methods across all evaluated metrics, including $S_m$, $F_β^{w}$, $E_m$, and $MAE$, demonstrating a more precise object-background separation and sharper boundary recovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13357 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Bi-CamoDiffusion: A Boundary-informed Diffusion Approach for Camouflaged Object Detection Suarez, Patricia L. Ramos, Leo Thomas Sappa, Angel D. Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Bi-CamoDiffusion is introduced, an evolution of the CamoDiffusion framework for camouflaged object detection. It integrates edge priors into early-stage embeddings via a parameter-free injection process, which enhances boundary sharpness and prevents structural ambiguity. This is governed by a unified optimization objective that balances spatial accuracy, structural constraints, and uncertainty supervision, allowing the model to capture of both the object's global context and its intricate boundary transitions. Evaluations across the CAMO, COD10K, and NC4K benchmarks show that Bi-CamoDiffusion surpasses the baseline, delivering sharper delineation of thin structures and protrusions while also minimizing false positives. Also, our model consistently outperforms existing state-of-the-art methods across all evaluated metrics, including $S_m$, $F_β^{w}$, $E_m$, and $MAE$, demonstrating a more precise object-background separation and sharper boundary recovery. |
| title | Bi-CamoDiffusion: A Boundary-informed Diffusion Approach for Camouflaged Object Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.13357 |