AI Paper Atlas

Research map / Image generation / Super-resolution

Pixel-Aware Stable Diffusion for Realistic Image Super-Resolution and Personalized Stylization

Tao Yang, Rongyuan Wu, Peiran Ren, Xuansong Xie, Lei Zhang

ECCV 2024 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 159 citations (OpenAlex)

Read the paper

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 degradation removal module (ablation)PASD · RealSRFID: 56.7890 -> 47.3440 FID; 0.3822 -> 0.2806 LPIPSImproved
add high-level information (classification, detection, caption) (ablation)PASD · RealSRFID: 50.2502 -> 47.3440Improved
add negative prompt with classifier-free guidance (ablation)PASD · RealSRFID: 52.3380 -> 47.3440 FID; runtime 8.7366 -> 14.5889 s; PSNR 27.0901 -> 25.9301Mixed
remove pixel-aware cross attention (add ControlNet features by plain addition)PASD · RealSRvisual structure consistencyHurt
increase adjustable-noise level alpha_a (ablation)PASD · RealSRPSNR vs QAlign: PSNR increases, QAlign decreases as alpha_a growsMixed
use diffusion-based Real-ISR rather than GAN-basedReal-ISR · RealSR / DIV2K / DRealSRPSNR/SSIMHurt
use PASD with swapped personalized base model for cartoonization (no extra training)FFHQ / Flicker2K · cartoonizationFID: 37.9589 -> 37.6698 (FFHQ vs ControlNet)Improved
swap base model to an aesthetic one for old photo restorationPASD · Old photo restorationFID: 262.1837 -> 240.2576 vs DiffBIRImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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