Recent denoising methods based on diffusion models typically formulate the task as a conditional generation process initialized from a standard Gaussian distribution. However, such stochastic initialization often leads to redundant sampling steps and unstable results due to the neglect of structured noise characteristics. To address these limitations, we propose a novel framework that directly bridges the probabilistic distributions of noisy and clean images while jointly modeling structured noise. We introduce Dual-diffusion Brownian Bridge Coupled Sampling (DBBCS) the first framework to incorporate Brownian bridge diffusion into image denoising. DBBCS synchronously models the distributions of clean images and structural noise via two coupled diffusion processes. Unlike conventional diffusion models, our method starts sampling directly from noisy observations and jointly optimizes image reconstruction and noise estimation through a coupled posterior sampling scheme. This allows for dynamic refinement of intermediate states by adaptively updating the sampling gradients using residual feedback from both image and noise paths. Specifically, DBBCS employs two parallel Brownian bridge models to learn the distributions of clean images and noise. During inference, their respective residual processes regulate each other to progressively enhance both denoising and noise estimation. A consistency constraint is enforced among the estimated noise, the reconstructed image, and the original noisy input to ensure stable and physically coherent results. Extensive experiments on standard benchmarks demonstrate that DBBCS achieves superior performance in both visual fidelity and quantitative metrics, offering a robust and efficient solution to image denoising.
Current diffusion model based image denoising methods suffer from semantic inconsistency and distortion due to their inability to maintain structural integrity, while diffusion models face two inherent limitations: (1) mandatory sampling initiation from pure Gaussian noise that mismatches denoising scenarios, and (2) uncontrollable uncertainty during stochastic sampling processes. Our work is motivated by the potential to harness precise edge information as conditional guidance to recalibrate diffusion sampling trajectories, thereby aligning the generative process with denoising objectives while preserving critical image structures. We propose a new image denoising framework, the EGDCF: Edge-Guided Diffusion networks with Coarse-to-Fine learning for image denoising, that synergizes edge-aware conditional guidance with a coarse-to-fine refinement mechanism through three key components: edge extractor, conditional diffusion model, and iterative denoising scheduler. EGDCF first uses a trainable Canny operator to extract multi-scale edge maps from noisy inputs, while calculating the number of denoising steps in the diffusion model’s reverse process based on the noise level of the input, thereby aligning the denoising trajectory with the actual noise distribution. Then, these structural priors are injected into the modified U-Net backbone network through attention based feature fusion, thereby guiding the sampling trajectory of the diffusion model’s reverse process. Finally, by fusing the noise input with the denoising results as the input for a new iteration, a clean denoised image can be obtained after multiple iterations. Quantitative evaluations on Gaussian and real-world noise datasets show effectiveness of our proposed method compared to state-of-the-art methods, particularly effective in high-noise regimes where conventional approaches fail.