AI Paper Atlas

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

High-Resolution Artwork Outpainting with Global Blueprint Guidance and Layout Control

Junha Kim, Hyunjoon Park, Donghyeon Cho

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 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 global guidance feature injection to Stage 2 (ablation)BlueOut · Artwork outpainting ablationFID: 22.2319 -> 9.3064Improved
add patch position token (ablation)BlueOut · Artwork outpainting ablationFID: 17.9578 -> 9.3064Improved
add forward-diffusion blueprint initialization (ablation)BlueOut · Artwork outpainting ablationFID: 9.6048 -> 9.3064Improved
use blueprint-guided Stage 2 instead of latent blending only (ablation)SD Inpainting (parallel) · Artwork outpainting ablationFID: 37.2675 -> 9.3064Improved
add layout conditioning (ablation)BlueOut Stage 2 · Artwork outpainting layout ablationlayout AP: 0.3973 -> 0.4336Improved
add layout conditioning (ablation)BlueOut Stage 2 · Artwork outpainting layout ablationFID: 9.7111 -> 9.3064Improved
use Stage 2 synthesis instead of super-resolving the Stage 1 blueprint (DRCT-L) (ablation)BlueOut · Stage 1 + SRFID: 22.0840 -> 9.3064Improved
increase guidance scale from 3.0 to 7.5 (ablation)BlueOut · Guidance scaleFID: 9.3064 -> 12.9130Hurt
weaken forward-init strength from 1.0 to 0.50 (ablation)BlueOut · Forward-init strengthlayout AP: 0.4336 -> 0.4979Mixed
use parallel Stage 2 on 8 GPUs vs ProOutBlueOut · Artwork outpainting (main)inference time (s): 18.31 -> 7.50Improved
use BlueOut instead of ProOut at 600% expansionBlueOut · Expansion ratio 600%FID: 89.84 -> 81.86Improved
run Stage 2 on a single GPU (ablation)BlueOut · Single-GPU inferenceinference time (s): 15.73 s vs 18.31 s ProOut, slower than SD Inpainting 13.43Mixed

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