AI Paper Atlas

Research map / Image generation / Super-resolution

Fast Adaptation to Super-Resolution Networks via Meta-Learning

Seobin Park, Jinsu Yoo, Donghyeon Cho, Jiwon Kim, Tae Hyun Kim

ECCV 2020 · Image generation › Super-resolution · approach: Real-world super-resolution · 92 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 MLSR meta-learning and 100 test-time stepsSRCNN · Urban100 x2 bicubicPSNR: 29.39 -> 29.54Improved
add MLSR meta-learning and 100 test-time stepsENET · Urban100 x2 bicubicPSNR: 30.38 -> 30.52Improved
add MLSR meta-learning and 100 test-time stepsIDN · Urban100 x2 bicubicPSNR: 31.95 -> 32.23Improved
add MLSR meta-learning and 20 test-time stepsRCAN · Urban100 x2 bicubicPSNR: 33.10 -> 33.32Improved
increase test-time steps from 20 to 100 (ablation)RCAN + MLSR · DIV2K test x2 bicubicPSNR: 35.75 -> 35.48Hurt
increase test-time steps from 5 to 100 (ablation)IDN + MLSR · BSD100 x2 bicubicPSNR: 32.17 -> 32.08Hurt
meta-train on Urban100 instead of DIV2K (ablation)IDN-ML · Urban100 40-image testPSNR: 32.37 -> 32.43Improved
increase test-time gradient steps from 0 to 100 (ablation)IDN-ML · Urban100 unknown 5x5 kernelPSNR: 23.48 -> 25.42Improved
fine-tune on the test image at test timeIDN · Urban100 x2 non-bicubic kernelPSNR: 23.49 -> 25.93Improved
replace ZSSR with meta-trained IDN using 100 stepsIDN-ML · Urban100 unknown kernelPSNR: 25.02 -> 25.42Improved
use large scale factors x3 and x4 with test-time fine-tuningIDN · Urban100 x3 and x4PSNR: 0.04dBNo clear effect

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