AI Paper Atlas

Research map / Image generation / Super-resolution

KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution

Jiahong Fu, Hong Wang, Qi Xie, Qian Zhao, Deyu Meng, Zongben Xu

ECCV 2022 · Image generation › Super-resolution · approach: Blind super-resolution · 38 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add 5 unfolded stages (S=0 to S=5) (ablation)KXNet · Set14PSNR: 25.74 -> 29.91Improved
increase stages from 5 to 10 (ablation)KXNet · Set14PSNR: 29.91 -> 30.57Improved
increase stages from 10 to 17 (ablation)KXNet · Set14PSNR: 30.57 -> 30.96Improved
increase stages from 17 to 19 (ablation)KXNet · Set14PSNR: 30.96 -> 31.14Improved
increase stages from 19 to 21 (ablation)KXNet · Set14PSNR: 31.14 -> 31.14No clear effect
increase stages from 19 to 21 (ablation)KXNet · Set14inference time (s): 0.59 -> 0.64Hurt
provide ground-truth blur kernel to X-net (ablation)KXNet · Set14PSNR: 31.97 -> 32.85Improved
provide ground-truth blur kernel to DAN (ablation)DAN · Set14PSNR: 31.97 -> 32.67Improved
KXNet instead of DAN under complex degradation (noise 0)blind SR · Urban100 (Setting 2, x3)PSNR: 25.82 -> 26.37Improved
KXNet instead of DAN with isotropic blurblind SR · Urban100 (Setting 1, x4)PSNR: 25.95 -> 26.18Improved
KXNet instead of DANblind SR · Set5 (Setting 1, x4)PSNR: 31.96 -> 31.94No clear effect
KXNet instead of DAN for inference speedblind SR · Set5 (Setting 2, x2)inference time (s): 0.52 -> 0.38Improved

Later papers that compared with this method

1 later accepted paper reports KXNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy