AI Paper Atlas

Research map / Image generation / Super-resolution

CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution

Cheeun Hong, Sungyong Baik, Heewon Kim, Seungjun Nah, Kyoung Mu Lee

ECCV 2022 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 46 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
use CADyQ dynamic bit-width instead of fixed 8-bit PAMSIDN x2 · Urban100 x2FQR / PSNR: FQR 8.00 -> 5.22; PSNR 31.39 -> 31.54Improved
use CADyQ instead of 4-bit DAQIDN x2 · Urban100 x2PSNR: 29.15 -> 31.54Improved
use CADyQ instead of 8-bit PAMSCARN x2 · Urban100 x2PSNR: 31.74 -> 31.87Improved
apply CADyQ on top of the LinQ quantization functionLinQ 8-bit · Urban100 x4FQR / PSNR: IDN 8.00 -> 6.85 FQR, PSNR 25.47 -> 25.60Improved
apply CADyQ on top of fully quantized FQSREDSR-baseline FQSR · Urban100 x4BitOPs / PSNR: BitOPs 19.8G -> 17.6G; PSNR 25.92 -> 25.90Improved
add candidate bit-width 6 to {4, 8} (ablation)CARN-CADyQ · Urban100 x4PSNR: 25.90 -> 25.94; FQR 5.02 -> 5.32Improved
add candidate bit-width 2 to {4, 6, 8} (ablation)CARN-CADyQ · Urban100 x4PSNR: 25.94 -> 25.61; FQR 5.32 -> 3.45Hurt
use smaller inference patches (192 to 48) (ablation)CARN-CADyQ · Urban100 x4BitOPs / PSNR: BitOPs 3.36G -> 3.12G; PSNR 25.95 -> 25.92Improved
use CADyQ patch-wise with bit selector instead of PAMS 8-bit image inferenceCARN · 4K imagelatency: 216.0 ms -> 202.9 msImproved
increase w_reg (ablation)CARN-CADyQ · DIV2K validationPSNRHurt

Later papers that compared with this method

1 later accepted paper reports CADYQ 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