AI Paper Atlas

Research map / Image generation / Super-resolution

Uncertainty Learning in Kernel Estimation for Multi-stage Blind Image Super-Resolution

Zhenxuan Fang, Weisheng Dong, Xin Li, Jinjian Wu, Leida Li, Guangming Shi

ECCV 2022 · Image generation › Super-resolution · approach: Blind super-resolution · 21 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 uncertainty learning to kernel estimation (ablation)kernel estimation network · average over 9 kernels, noise 20kernel MAE: 0.252 -> 0.172Improved
add uncertainty learning to kernel estimation (ablation)kernel estimation network · average over 9 kernels, noise 0kernel MAE: 0.190 -> 0.146Improved
add uncertainty learning to kernel estimation (ablation)KULNet · Set14 x4 (noise 0)PSNR: 27.49 -> 27.81Improved
add uncertainty learning to kernel estimation (ablation)KULNet · Urban100 x2 (noise 0)PSNR: 27.75 -> 28.16Improved
add uncertainty learning to kernel estimation (ablation)KULNet · Set5 x2 (noise 20)PSNR: 29.27 -> 29.54Improved
add KL regularization (lambda 0 -> 0.001) (ablation)KULNet · Set14 x4PSNR: 26.49 -> 26.76Improved
add KL regularization (lambda 0 -> 0.001) (ablation)KULNet · BSD100 x4PSNR: 25.95 -> 26.12Improved
raise KL weight too high (0.001 -> 1) (ablation)KULNet · Set14 x4PSNR: 26.76 -> 25.89Hurt
raise KL weight from 0.001 to 0.1 (ablation)KULNet · BSD100 x4PSNR: 26.12 -> 25.62Hurt
add dense connections (ablation)KULNet · Set14 x4PSNR: 0.13 dBImproved
increase number of stages T (ablation)KULNet · Set14 x2 and x4PSNRImproved
replace MANet with KULNetblind SR · Urban100 x4 (noise 0)PSNR: 24.49 -> 25.07Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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