AI Paper Atlas

Research map / Image generation / Super-resolution

Fair and Faithful: A Diffusion-Enhanced Dataset and Hybrid State-Space Mamba for Face Super-Resolution

Tao Wang, Peiwen Xia, Bowen Tang, Jinwei Chen, Kaihao Zhang, Bo Li

ECCV 2026 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 0 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 region-adaptive scan to global scan (ablation)GLASNet · SFHQFSR scan ablationPSNR: 30.13 -> 30.73Improved
use region-adaptive scan alone instead of global scan (ablation)GLASNet · SFHQFSR scan ablationPSNR: 30.13 -> 30.41Improved
apply global scan first then region-adaptive scan (instead of reverse) (ablation)GLASNet · SFHQFSR scan ablationPSNR: 30.73 -> 30.86Improved
add channel attention to refiner (ablation)GLASNet refiner · SFHQFSR refiner ablationPSNR: 28.30 -> 29.92Improved
add spatial attention to refiner (ablation)GLASNet refiner · SFHQFSR refiner ablationSSIM: 0.8312 -> 0.8214Mixed
add frequency attention to refiner (ablation)GLASNet refiner · SFHQFSR refiner ablationPSNR: 30.20 -> 30.86Improved
add frequency attention to refiner (ablation)GLASNet refiner · SFHQFSR refiner ablationSSIM: 0.8214 -> 0.8451Improved
increase HSSMG groups from 6 to 8 (ablation)GLASNet · SFHQFSRPSNR: 30.86 -> 30.90No clear effect
increase HSSMG groups from 2 to 6 (ablation)GLASNet · SFHQFSRPSNR: 30.18 -> 30.86Improved
train SFMNet on SFHQFSR instead of FFHQSFMNet · Helen BI x8PSNR: 24.02 -> 24.34Improved
train SFMNet on SFHQFSR instead of FFHQSFMNet · CelebA-test BI x8PSNR: 28.90 -> 29.28Improved
train SPARNet on SFHQFSR instead of FFHQSPARNet · CelebA-test BI x8PSNR: 29.09 -> 29.11No 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