AI Paper Atlas

Research map / Image generation / Image restoration

Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization

Ming-Yang Ho, Che-Ming Wu, Min-Sheng Wu, ‪Yufeng Jane Tseng

ECCV 2024 · Image generation › Image restoration · approach: Image harmonization and color transformation · 11 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
estimate pixel-level statistics (DN) instead of image-level (TIN) statisticsCUT inference · real2paintFID: 249.612 -> 237.202Improved
estimate pixel-level statistics (DN) instead of patch-level kernelized statistics (KIN)CUT inference · ANHIR (breast)FID: 91.443 -> 68.616Improved
replace patch-wise IN with DN at inferenceCUT · ANHIR (breast)FID: 64.202 (patch-wise IN) vs 68.616No clear effect
use DN instead of TIN for domain differentiationCUT · real2paintdomain differentiation accuracy: 0.556 -> 0.986Improved
use DN instead of patch-wise IN, TIN or KIN in human evaluationCUT · summer2autumn (experts, best quality)preferred (%): 82.86 (DN) vs 11.43 (KIN)Improved
reformulate bilinear interpolation as fast interpolation (ablation)DN · 4,302x3,024 imageruntime (s): 192.50 -> 8.28Improved
precompute interpolation matrices (ablation)DN · 4,302x3,024 imageruntime (s): 8.28 -> 5.51Improved
add prefetching parallelism to run caching and inference in one pass (ablation)DN · 4,302x3,024 imageruntime (s): 5.51 -> 4.35Improved
increase interpolating granularity from 1 pixel to 512 pixels (ablation)DN · qualitative ablationtiling artifactsHurt
run DN single-pass versus KIN two-stageDN · 4,302x3,024 imageGPU VRAM (mb): 3145 (KIN) -> 4157Hurt

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