Chao Xu, Yong Liu, Jiangning Zhang, Chengjie Wang, Yabiao Wang, Xuhai Chen
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2304.03542")
get_code_for_paper("2304.03542")
have("2304.03542")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2304.03542.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2304.03542)
Connect an agent — have() is free.