Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution
This work addresses the challenge of training super-resolution models for real-world images, which often suffer from complex degradations, by providing a method to generate synthetic training data, though it is incremental as it builds on existing degradation modeling approaches.
The paper tackles the problem of super-resolution for real-world images with complex degradations by introducing a framework that synthesizes realistic low-resolution images from a single high-resolution image using latent flow matching, enabling the creation of large-scale training datasets and resulting in significantly better high-resolution outcomes for both traditional and arbitrary-scale models.
While deep learning-based super-resolution (SR) methods have shown impressive outcomes with synthetic degradation scenarios such as bicubic downsampling, they frequently struggle to perform well on real-world images that feature complex, nonlinear degradations like noise, blur, and compression artifacts. Recent efforts to address this issue have involved the painstaking compilation of real low-resolution (LR) and high-resolution (HR) image pairs, usually limited to several specific downscaling factors. To address these challenges, our work introduces a novel framework capable of synthesizing authentic LR images from a single HR image by leveraging the latent degradation space with flow matching. Our approach generates LR images with realistic artifacts at unseen degradation levels, which facilitates the creation of large-scale, real-world SR training datasets. Comprehensive quantitative and qualitative assessments verify that our synthetic LR images accurately replicate real-world degradations. Furthermore, both traditional and arbitrary-scale SR models trained using our datasets consistently yield much better HR outcomes.