CODiff: One-Step Diffusion Model for Camouflaged Object Detection

Xiaotong Fu, Qian Liu, Qihang Zhou, Wenchao Meng, Qinmin Yang, Shibo He
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:31977-31991, 2026.

Abstract

Diffusion-based camouflaged object detection (COD) has recently shown great potential. In contrast to existing approaches that rely on multiple sample steps to refine the predicted masks, we propose CODiff, which reformulates the diffusion process to enable one-step mask prediction while maintaining competitive accuracy. Specifically, we first establish the theoretical feasibility of one-step sampling for COD. Based on this, we design a dedicated network for one-step inference with a global semantic guidance mechanism to guide the denoising process globally and hierarchical condition integration blocks to provide fine-grained structural semantics. In addition, we design a straight-forward regularization to learn better intermediate features by bridging the representation gap between the condition backbone and the diffusion model. Extensive experiments demonstrate that CODiff achieves state-of-the-art performance across multiple benchmarks, improving MAE by over 22% on the challenging COD10K dataset. Code is available at https://github.com/KiiSooo/CODiff.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-fu26l, title = {{COD}iff: One-Step Diffusion Model for Camouflaged Object Detection}, author = {Fu, Xiaotong and Liu, Qian and Zhou, Qihang and Meng, Wenchao and Yang, Qinmin and He, Shibo}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {31977--31991}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/fu26l/fu26l.pdf}, url = {https://proceedings.mlr.press/v306/fu26l.html}, abstract = {Diffusion-based camouflaged object detection (COD) has recently shown great potential. In contrast to existing approaches that rely on multiple sample steps to refine the predicted masks, we propose CODiff, which reformulates the diffusion process to enable one-step mask prediction while maintaining competitive accuracy. Specifically, we first establish the theoretical feasibility of one-step sampling for COD. Based on this, we design a dedicated network for one-step inference with a global semantic guidance mechanism to guide the denoising process globally and hierarchical condition integration blocks to provide fine-grained structural semantics. In addition, we design a straight-forward regularization to learn better intermediate features by bridging the representation gap between the condition backbone and the diffusion model. Extensive experiments demonstrate that CODiff achieves state-of-the-art performance across multiple benchmarks, improving MAE by over 22% on the challenging COD10K dataset. Code is available at https://github.com/KiiSooo/CODiff.} }
Endnote
%0 Conference Paper %T CODiff: One-Step Diffusion Model for Camouflaged Object Detection %A Xiaotong Fu %A Qian Liu %A Qihang Zhou %A Wenchao Meng %A Qinmin Yang %A Shibo He %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-fu26l %I PMLR %P 31977--31991 %U https://proceedings.mlr.press/v306/fu26l.html %V 306 %X Diffusion-based camouflaged object detection (COD) has recently shown great potential. In contrast to existing approaches that rely on multiple sample steps to refine the predicted masks, we propose CODiff, which reformulates the diffusion process to enable one-step mask prediction while maintaining competitive accuracy. Specifically, we first establish the theoretical feasibility of one-step sampling for COD. Based on this, we design a dedicated network for one-step inference with a global semantic guidance mechanism to guide the denoising process globally and hierarchical condition integration blocks to provide fine-grained structural semantics. In addition, we design a straight-forward regularization to learn better intermediate features by bridging the representation gap between the condition backbone and the diffusion model. Extensive experiments demonstrate that CODiff achieves state-of-the-art performance across multiple benchmarks, improving MAE by over 22% on the challenging COD10K dataset. Code is available at https://github.com/KiiSooo/CODiff.
APA
Fu, X., Liu, Q., Zhou, Q., Meng, W., Yang, Q. & He, S.. (2026). CODiff: One-Step Diffusion Model for Camouflaged Object Detection. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:31977-31991 Available from https://proceedings.mlr.press/v306/fu26l.html.

Related Material