Better "CMOS" Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution
This addresses a domain-specific problem in computer vision for image processing, offering an incremental improvement over existing methods.
The paper tackles the problem of blind image super-resolution with space-variant blur, which causes performance drops in real applications, by introducing new datasets and a Cross-MOdal fuSion network (CMOS) that estimates blur and semantics simultaneously, achieving a PSNR/SSIM improvement of +1.91/+0.0048 on NYUv2-BSR compared to MANet.
Most of the existing blind image Super-Resolution (SR) methods assume that the blur kernels are space-invariant. However, the blur involved in real applications are usually space-variant due to object motion, out-of-focus, etc., resulting in severe performance drop of the advanced SR methods. To address this problem, we firstly introduce two new datasets with out-of-focus blur, i.e., NYUv2-BSR and Cityscapes-BSR, to support further researches of blind SR with space-variant blur. Based on the datasets, we design a novel Cross-MOdal fuSion network (CMOS) that estimate both blur and semantics simultaneously, which leads to improved SR results. It involves a feature Grouping Interactive Attention (GIA) module to make the two modalities interact more effectively and avoid inconsistency. GIA can also be used for the interaction of other features because of the universality of its structure. Qualitative and quantitative experiments compared with state-of-the-art methods on above datasets and real-world images demonstrate the superiority of our method, e.g., obtaining PSNR/SSIM by +1.91/+0.0048 on NYUv2-BSR than MANet.