{"ID":2884065,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.07214","arxiv_id":"2508.07214","title":"Unsupervised Real-World Super-Resolution via Rectified Flow Degradation Modelling","abstract":"Unsupervised real-world super-resolution (SR) faces critical challenges due to the complex, unknown degradation distributions in practical scenarios. Existing methods struggle to generalize from synthetic low-resolution (LR) and high-resolution (HR) image pairs to real-world data due to a significant domain gap. In this paper, we propose an unsupervised real-world SR method based on rectified flow to effectively capture and model real-world degradation, synthesizing LR-HR training pairs with realistic degradation. Specifically, given unpaired LR and HR images, we propose a novel Rectified Flow Degradation Module (RFDM) that introduces degradation-transformed LR (DT-LR) images as intermediaries. By modeling the degradation trajectory in a continuous and invertible manner, RFDM better captures real-world degradation and enhances the realism of generated LR images. Additionally, we propose a Fourier Prior Guided Degradation Module (FGDM) that leverages structural information embedded in Fourier phase components to ensure more precise modeling of real-world degradation. Finally, the LR images are processed by both FGDM and RFDM, producing final synthetic LR images with real-world degradation. The synthetic LR images are paired with the given HR images to train the off-the-shelf SR networks. Extensive experiments on real-world datasets demonstrate that our method significantly enhances the performance of existing SR approaches in real-world scenarios.","short_abstract":"Unsupervised real-world super-resolution (SR) faces critical challenges due to the complex, unknown degradation distributions in practical scenarios. Existing methods struggle to generalize from synthetic low-resolution (LR) and high-resolution (HR) image pairs to real-world data due to a significant domain gap. In thi...","url_abs":"https://arxiv.org/abs/2508.07214","url_pdf":"https://arxiv.org/pdf/2508.07214v1","authors":"[\"Hongyang Zhou\",\"Xiaobin Zhu\",\"Liuling Chen\",\"Junyi He\",\"Jingyan Qin\",\"Xu-Cheng Yin\",\"Zhang xiaoxing\"]","published":"2025-08-10T07:27:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"eess.IV\"]","methods":"[]","has_code":false}