AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Creatively Upscaling Images with Global-Regional Priors

Yurui Qian, Qi Cai, Yingwei Pan, Ting Yao, Tao Mei

IJCV 2025 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 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 Global Structure Prior (ablation)C-Upscale · LAION-5B synthetic 2048x2048MUSIQ: 73.11 -> 74.02Improved
add Regional Attention Prior (ablation)C-Upscale · LAION-5B synthetic 2048x2048CLIP score: 0.8608 -> 0.8687Improved
add Regional Semantic Prior (ablation)C-Upscale · LAION-5B synthetic 2048x2048MUSIQ: 72.80 -> 74.02Improved
add Regional Semantic Prior (ablation)C-Upscale · LAION-5B synthetic 2048x2048FID: 67.62 -> 66.72Improved
add Global Structure Prior (ablation)C-Upscale · LAION-5B synthetic 2048x2048LPIPS: 0.2793 -> 0.2766Improved
increase GSP step size s from 0.2 to 1.0 (ablation)C-Upscale GSP · qualitative, SDXLvisual artifacts: s = 0, 0.2, 1.0Hurt
increase GSP step size from 0 to 0.2 (cosine schedule) (ablation)C-Upscale GSP · qualitative, SDXLobject repetition: s = 0, 0.2, and 1.0Improved
use linear decreasing instead of cosine scheduler in GSP (ablation)C-Upscale GSP · qualitative, SDXLvisual artifactsHurt
use linear increasing scheduler in GSP (ablation)C-Upscale GSP · qualitative, SDXLsharpnessHurt
increase region overlap from 512 to 768 (ablation)C-Upscale · SDXL 4096x4096inference time: {0,512,768}Hurt
replace progressive upscaling and 50-step noise denoising with diffuse-then-denoiseDemoFusion-style upscaling · LAION-5B synthetic 4096x4096inference time: 14min -> 4minImproved
use Hyper-SDXL few-step model and vLLM for LLaVAC-Upscale · 1024 to 4096 upscalinginference time: ~ 4 minutes to ~ 30 secondsImproved

Earlier methods this paper compares with

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