Bi-CamoDiffusion: A Boundary-informed Diffusion Approach for Camouflaged Object Detection

TL;DR

Bi-CamoDiffusion is a novel boundary-informed diffusion model that significantly improves camouflaged object detection by integrating edge priors and optimizing boundary accuracy, outperforming existing methods on multiple benchmarks.

Contribution

It introduces a boundary-aware diffusion framework with edge prior integration and a unified optimization objective for enhanced camouflaged object detection.

Findings

Outperforms state-of-the-art methods across all metrics

Achieves sharper boundary delineation and reduces false positives

Demonstrates superior performance on CAMO, COD10K, and NC4K benchmarks

Abstract

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 $S_m$, $F_{\beta}^{w}$, $E_m$, and $MAE$, demonstrating a more precise object-background separation and sharper boundary recovery.