Robust Denoising of Structure Noise Through Dual-Diffusion Brownian Bridge Modeling and Coupled Sampling
Open Access
- 30 October 2025
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 14 (21) , 4243
Abstract
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.Keywords
Funding Information
- Guangxi Key Research and Development Program (AB25069247, AB25069280)
This publication has 38 references indexed in Scilit:
- DMF-SIM: Dual-Model Framework for super-resolution reconstruction and denoising in Structured Illumination MicroscopyPattern Recognition, 2025
- PyramidPCD: A novel pyramid network for point cloud denoisingPattern Recognition, 2024
- Diffusion probabilistic priors for zero‐shot low‐dose CT image denoisingMedical Physics, 2024
- New non-local mean methods for MRI denoising based on global self-similarity between valuesComputers in Biology and Medicine, 2024
- A cross Transformer for image denoisingInformation Fusion, 2023
- Image denoising in the deep learning eraArtificial Intelligence Review, 2022
- SRNet: Sparse representation-based network for image denoisingDigital Signal Processing, 2022
- Joint image denoising with gradient direction and edge-preserving regularizationPattern Recognition, 2022
- Deep Sparse Representation Based Image Restoration With Denoising PriorIEEE Transactions on Circuits and Systems for Video Technology, 2022
- An Explicit Solution for Image Restoration using Markov Random FieldsJournal of Signal Processing Systems, 2019