AI Paper Atlas

Research map / Image generation / Super-resolution

Unsupervised Real-World Super-Resolution: A Domain Adaptation Perspective

Wei Wang, Haochen Zhang, Zehuan Yuan, Changhu Wang

ICCV 2021 · Image generation › Super-resolution · approach: Real-world super-resolution · 72 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 feature alignment loss L_align on top of the regularization losses (ablation)Domain-adaptation SR network · NTIRE 2020 Track 1LPIPS: 0.373 -> 0.296Improved
add feature alignment loss L_align on top of the regularization losses (ablation)Domain-adaptation SR network · NTIRE 2020 Track 1SSIM: 0.663 -> 0.690Improved
add feature alignment loss L_align on top of the regularization losses (ablation)Domain-adaptation SR network · NTIRE 2020 Track 1PSNR: 25.53 -> 25.14Hurt
add feature domain regularization losses (L_res, L_sty, L_idt, L_cyc) to the alignment-only model (ablation)Domain-adaptation SR network · NTIRE 2020 Track 1LPIPS: 0.448 -> 0.296Improved
add feature alignment loss alone to the base model (ablation)Base model (L_rec only) · NTIRE 2020 Track 1LPIPS: 0.436 -> 0.448Hurt
add feature alignment loss alone to the base model (ablation)Base model (L_rec only) · NTIRE 2020 Track 1PSNR: 25.65 -> 25.20Hurt
use full proposed framework instead of base model (ablation)Base model (L_rec only) · NTIRE 2020 Track 1LPIPS: 0.436 -> 0.296Improved
train on source LR with complex degradation instead of bicubic downsampling (ablation)Base model · NTIRE 2020 Track 1LPIPSImproved
add proposed domain adaptation framework to base model for either source LR synthesis (ablation)Base model · NTIRE 2020 Track 1LPIPSImproved

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