AI Paper Atlas

Research map / Image generation / Super-resolution

PatchScaler: An Efficient Patch-Independent Diffusion Model for Image Super-Resolution

Yong Liu, Hang Dong, Jinshan Pan, Qingji Dong, Kai Chen, Rongxiang Zhang, Lean Fu, Fei Wang

ICCV 2025 · Image generation › Super-resolution · approach: Diffusion-based super-resolution · 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
use texture prompt instead of text prompt (ablation)PatchScaler · RealSet110ManIQA: 0.4849 -> 0.5442Improved
use texture prompt instead of text prompt (ablation)PatchScaler · RealSet110CLIPIQA: 0.7890 -> 0.8213Improved
use texture prompt instead of text prompt (ablation)PatchScaler · RealSet110MUSIQ: 66.79 -> 70.97Improved
add PGS and GRM to StableSR training-freeStableSR · RealSet110ManIQA: 0.3856 -> 0.5035Improved
add PGS and GRM to StableSR training-freeStableSR · RealSet110MUSIQ: 62.08 -> 65.54Improved
add PGS and GRM to StableSR training-freeStableSR · RealSet110CLIPIQA: 0.7851 -> 0.7809No clear effect
add PGS to StableSRStableSR · x4 512->2048 SRruntime (s): 35.22 -> 8.53Improved
use two GPUs for patch groupsPatchScaler · x4 512->2048 SRruntime (s): 3.41 -> 2.26Improved
reduce intermediate time steps from [1000,1000,1000] to [400,700,1000] (ablation)PatchScaler · RealSet110quality metricsNo clear effect
reduce time steps further below [400,700,1000] (ablation)PatchScaler · RealSet110quality metricsHurt
reduce sampling steps from [20,20,20] to [8,14,20] (ablation)PatchScaler · RealSet110quality metricsNo clear effect
reduce sampling steps further below [8,14,20] (ablation)PatchScaler · RealSet110quality metricsHurt

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