D3BSR: Blind Super-Resolution via Diffusion-Based Disentangled Degradation Representation
- 4 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 1639-1653
Abstract
Existing Blind Super-Resolution (BSR) methods are mostly trained on artificial synthetic degradation data pairs or rely on specific degradation priors, which lead to poor performance due to the trained degradation mismatch between other unknown complex degradations in real-world scenarios. To tackle this problem, we propose a novel Diffusion-based Disentangled Degradation representation method for BSR, dubbed D3BSR, which disentangles arbitrary unknown degradation into structure and texture degradations to enhance perception and fidelity quality individually. Specifically, the structure degradation is optimized by degradation distribution transition with a self-supervised collaborative learning strategy to recursively minimize the perception error. The texture degradation is restored through posterior sampling controlled by a fidelity coefficient to leverage rich texture priors encapsulated in a pre-trained diffusion model for preserving fidelity. The degraded image is super-resolved using an analytical solution with the pseudo inverse of the structural and texture degradation, which achieves a controllable trade-off between perception and fidelity and does not rely on any degradation priors or extra-supervised training. Extensive experiments on the nine heavily degraded synthetic and real-world natural and face datasets demonstrate that our D3BSR outperforms SOTA methods on the diverse metrics in reconstruction faithfulness and perceptual quality.Keywords
Funding Information
- National Natural Science Foundation of China (6250073164)
- National Natural Science Foundation of China (61872112)
- National Natural Science Foundation of China (61076096)
This publication has 57 references indexed in Scilit:
- DiffBIR: Toward Blind Image Restoration with Generative Diffusion Prior2024
- Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization2024
- VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder2022
- From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution2022
- Component Divide-and-Conquer for Real-World Image Super-Resolution2020
- Blind Face Restoration via Deep Multi-scale Component Dictionaries2020
- Face Super-Resolution Guided by 3D Facial Priors2020
- The 2018 PIRM Challenge on Perceptual Image Super-Resolution2019
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- On Single Image Scale-Up Using Sparse-Representations2012