AI Paper Atlas

Research map / Image generation / Super-resolution

RankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank

Wenlong Zhang, Yihao Liu, Chao Dong, Yu Qiao

TPAMI 2021 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 76 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 rank-content loss from a Ranker to SRGANSRGAN · PIRM-Test x4NIQE: 2.71 -> 2.51Improved
add rank-content loss from a Ranker to SRGANSRGAN · BSD100 x4NIQE: 3.29 -> 3.01Improved
add rank-content loss from a Ranker to SRGANSRGAN · PIRM-Test x4PSNR: 25.60 -> 25.62No clear effect
label rank pairs by metric rank instead of model classification (ablation)RankSRGAN · PIRM-Test x4NIQEImproved
use ground-truth HR instead of ESRGAN as best rank-dataset level (ablation)RankSRGAN · PIRM-Test x4PSNR: NIQE 2.51 -> 2.58, PSNR 25.60 -> 26.00Mixed
train Ranker with margin-ranking instead of MSE regression (ablation)RankSRGAN (NIQE Ranker) · PIRM-Test x4NIQE: 2.53 -> 2.51Improved
train Ranker with margin-ranking instead of MSE regression (ablation)RankSRGAN (Ma Ranker) · PIRM-Test x410-Ma: 1.43 -> 1.38Improved
rank labels from PI instead of NIQE (ablation)RankSRGAN · PIRM-Test x4PI: 1.95 -> 1.94Improved
add MSE loss weight alpha2 to rank-content loss (ablation)RankSRGAN · PIRM-Test x4PSNR: PSNR 25.62 -> 26.62, NIQE 2.51 -> 2.72Mixed
use deeper Ranker VGG-12 instead of VGG-8 (ablation)Ranker · Rank validation setSROCC: 0.83 -> 0.88Improved
use VGG-16 instead of VGG-12 Ranker (ablation)Ranker · Rank validation setSROCC: 0.88 -> 0.88No clear effect
change monotonic function (sigmoid, exponential, identity) of rank-content loss (ablation)RankSRGAN · PIRM-Test x4NIQENo clear effect

Later papers that compared with this method

4 later accepted papers report RankSRGAN as a baseline in their results tables; 3 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