AI Paper Atlas

Research map / Image generation / Super-resolution

ATD: Improved Transformer With Adaptive Token Dictionary for Image Restoration

Leheng Zhang, Wei Long, Yawei Li, Xingyu Zhou, Xiaorui Zhao, Shuhang Gu

TPAMI 2026 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 3 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 token dictionary cross-attention (TDCA) to baseline (ablation)ATD-light · Urban100 x4 (ATD-light)PSNR: 26.40 -> 26.46Improved
add token dictionary cross-attention (TDCA) to baseline (ablation)ATD-light · Manga109 x4 (ATD-light)PSNR: 30.84 -> 30.92Improved
add adaptive category-based self-attention (ACMSA) after TDCA (ablation)ATD-light · Urban100 x4 (ATD-light)PSNR: 26.46 -> 26.70Improved
add adaptive category-based self-attention (ACMSA) after TDCA (ablation)ATD-light · Manga109 x4 (ATD-light)PSNR: 30.92 -> 31.19Improved
add category-aware FFN (CFFN) (ablation)ATD-light · Urban100 x4 (ATD-light)PSNR: 26.70 -> 26.76Improved
add category-aware FFN (CFFN) (ablation)ATD-light · Manga109 x4 (ATD-light)PSNR: 31.19 -> 31.21Improved
use reparameterized scaling factor tau' at dictionary size 128 (ablation)ATD-light · Urban100 x4 (ATD-light)PSNR: 26.70 -> 26.76Improved
increase dictionary size M from 64 to 128 with original scaling factor (ablation)ATD-light · Urban100 x4 (ATD-light)PSNR: 26.73 -> 26.70Hurt
increase sub-category size n_s from 0 (no ACMSA) to 128 (ablation)ATD-light · Urban100 x4 (ATD-light)PSNR: 26.46 -> 26.76Improved
increase sub-category size n_s from 128 to 256 (ablation)ATD-light · Urban100 x4 (ATD-light)PSNR: 26.76 -> 26.75No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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