AI Paper Atlas

Research map / Image generation / Super-resolution

KOALAnet: Blind Super-Resolution Using Kernel-Oriented Adaptive Local Adjustment

Soo Ye Kim, Hyeonjun Sim, Munchurl Kim

CVPR 2021 · Image generation › Super-resolution · approach: Blind super-resolution · 90 citations (OpenAlex)

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
use KOALAnet instead of the strongest listed baselineBlind SR · random anisotropic degradation benchmarks, ×2 and ×4PSNR: 33.08 vs 28.61; 30.35 vs 26.63; 29.70 vs 26.86; 27.19 vs 24.11; 32.61 vs 26.19; 32.55 vs 28.90; 31.89 vs 30.36; 30.28 vsImproved
add KOALA modules with k parameters to the upsampler (ablation)KOALAnet · DIV2K-val ×4PSNR: 29.20 -> 29.40Improved
add m parameters to KOALA modules with k (ablation)KOALAnet · DIV2K-val ×4PSNR: 29.40 -> 29.44Improved
replace estimated degradation kernels with ground-truth kernels (ablation)KOALAnet · DIV2K-val ×4PSNR: 29.44 -> 29.67Improved
replace U-Net with ResNet in the downsampling network (ablation)KOALAnet downsampler · DIV2K-val ×1/4PSNR: 49.50 -> 47.79Hurt
remove residual connections from downsampling-network ResBlocks (ablation)KOALAnet downsampler · DIV2K-val ×1/4PSNR: 49.50 -> 47.85Hurt
estimate uniform instead of spatially-variant kernels (ablation)KOALAnet downsampler · DIV2K-val ×1/4PSNR: 49.50 -> 45.78Hurt
remove normalization from predicted degradation kernels (ablation)KOALAnet downsampler · DIV2K-val ×1/4PSNR: 49.50 -> 49.15Hurt
use the downsampling network's estimated spatially-variant kernelsKOALAnet · DIV2K-valL2 kernel error: KernelGAN 0.0230; BlindSR 0.0152; KOALAnet 0.0010Improved
use kernel-aware local adjustment rather than an upsampler alone (ablation)SR on shallow-DoF aesthetic images · artistic photographs with intentional blurpreservation of intended blurImproved

Later papers that compared with this method

1 later accepted paper reports KOALAnet as a baseline in their results tables; 1 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