AI Paper Atlas

Research map / Image generation / Super-resolution

AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution

Fangzhou Luo, Xiaolin Wu, Yanhui Guo

NeurIPS 2023 · Image generation › Super-resolution · approach: Blind super-resolution · 2 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 adversarial perturbation, neural degradation and identity init to classical bicubic SR training (ablation)AND (ANDNet/ANDGAN) · RealSR (x4)PSNR of ANDNet: 26.53 -> 28.47Improved
add adversarial perturbation, neural degradation and identity init to classical bicubic SR training (ablation)AND (ANDNet/ANDGAN) · RealSR (x4)LPIPS of ANDGAN: 0.4245 -> 0.2326Improved
add neural degradation (with identity init) to adversarial noise training (ablation)AND (ANDNet/ANDGAN) · RealSR (x4)PSNR of ANDNet: 26.60 -> 28.47Improved
replace additive adversarial noise with adversarial neural degradation (ablation)AND (ANDNet/ANDGAN) · RealSR (x4)LPIPS of ANDGAN: 0.4194 -> 0.2326Improved
add adversarial perturbation to neural degradation with identity init (vs synthetic augmentation) (ablation)AND (ANDNet/ANDGAN) · RealSR (x4)PSNR of ANDNet: 27.31 -> 28.47Improved
add adversarial perturbation to neural degradation with identity init (vs synthetic augmentation) (ablation)AND (ANDNet/ANDGAN) · RealSR (x4)LPIPS of ANDGAN: 0.3089 -> 0.2326Improved
add identity initialization of the degradation network instead of random Xavier init (ablation)AND (ANDNet/ANDGAN) · RealSR (x4)PSNR of ANDNet: 11.84 -> 28.47Improved
adversarial noise training instead of classical bicubic training (adversarial noise only) (ablation)AND (ANDNet/ANDGAN) · RealSR (x4)PSNR of ANDNet: 26.53 -> 26.60No clear effect
ANDNet vs DCLS, DAN, DASR baselines on four real-world SR benchmarksANDNet · RealSR, DRealSR, SupER, ImgPairsPSNR: 27.83 -> 28.47 (RealSR vs DCLS)Improved
ANDGAN vs perceptual baselines (SwinIR-Real, DASR, Real-ESRGAN)ANDGAN · RealSR, DRealSR, SupER, ImgPairsLPIPS: 0.2515 -> 0.2326 (RealSR vs SwinIR-Real)Improved
ANDNet LPIPS vs best baseline on DRealSR and SupERANDNet · DRealSR / SupERLPIPS: 0.2739 vs 0.3381 (DRealSR)Hurt
adversarial degradation training cost vs plain ESRGAN trainingESRGAN · training cost per stepTFLOPs: 8.92 -> 57.85 TFLOPs (6.49x)Hurt

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