Zhang, HaiyangJiang, MengyuLiu, LiangChaine, RaphaëlleDeng, ZhigangKim, Min H.2023-10-092023-10-092023978-3-03868-234-9https://doi.org/10.2312/pg.20231270https://diglib.eg.org:443/handle/10.2312/pg20231270To achieve promising results on blind image super-resolution (SR), some Unsupervised Degradation Prediction (UDP) methods narrow the domain gap between the degradation embedding space and the SR feature space by fusing the degradation embedding with the additional content embedding before multi-stage SR. However, fusing these two embeddings before multi-stage SR is inflexible, due to the variation of the domain gap at each SR stage. To address this issue, we propose the Multi-Stage Degradation and Content Embedding Fusion (MDCF), which adaptively fuses the degradation embedding with the content embedding at each SR stage rather than before multi-stage SR. Based on the MDCF, we introduce a novel UDP method, called MDCFnet, which contains an additional Dual-Path Local and Global encoder (DPLG) to extract the degradation embedding and the content embedding separately. Specially, DPLG diversifies receptive fields to enrich the degradation embedding and combines local and global features to optimize the content embedding. Extensive experiments on real images and several benchmarks demonstrate that the proposed MDCFnet can outperform the existing UDP methods and achieve competitive performance on PSNR and SSIM even compared with the state-of-the-art SKP methods.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies -> ReconstructionComputing methodologiesReconstruction10.2312/pg.2023127047-559 pages