DeeDSR: Towards Real-World Image Super-Resolution via Degradation-Aware Stable Diffusion
This work improves super-resolution for real-world images, which is incremental as it builds on existing diffusion models by adding degradation awareness.
The paper tackles the problem of real-world image super-resolution by addressing global degradation impacts that reduce semantic fidelity, introducing a degradation-aware framework that recovers semantically precise and photorealistic details and demonstrates state-of-the-art performance across benchmarks.
Diffusion models, known for their powerful generative capabilities, play a crucial role in addressing real-world super-resolution challenges. However, these models often focus on improving local textures while neglecting the impacts of global degradation, which can significantly reduce semantic fidelity and lead to inaccurate reconstructions and suboptimal super-resolution performance. To address this issue, we introduce a novel two-stage, degradation-aware framework that enhances the diffusion model's ability to recognize content and degradation in low-resolution images. In the first stage, we employ unsupervised contrastive learning to obtain representations of image degradations. In the second stage, we integrate a degradation-aware module into a simplified ControlNet, enabling flexible adaptation to various degradations based on the learned representations. Furthermore, we decompose the degradation-aware features into global semantics and local details branches, which are then injected into the diffusion denoising module to modulate the target generation. Our method effectively recovers semantically precise and photorealistic details, particularly under significant degradation conditions, demonstrating state-of-the-art performance across various benchmarks. Codes will be released at https://github.com/bichunyang419/DeeDSR.