AI Paper Atlas

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

SceneComposer: Any-Level Semantic Image Synthesis

Yu Zeng, Zhe Lin, Jianming Zhang, Qing Liu, John Collomosse, Jason Kuen, Vishal M. Patel

CVPR 2023 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 40 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 the unified any-level model instead of the text-to-image-only baseline (ablation)SceneComposer · OpenLayout-COCO, precision 0FID: 32.83 -> 32.09Improved
Use the unified any-level model instead of the fixed-level layout baseline (ablation)SceneComposer · OpenLayout-COCO, precision 4SS Score: .5729 -> .6978Improved
Increase layout precision from 0 to 6SceneComposer · OpenLayoutSS Score: .436 -> .558Improved
Increase layout precision from 0 to 6SceneComposer · OpenLayout-COCOSS Score: .572 -> .736Improved
Increase layout precision from 0 to 6SceneComposer · OpenLayout-COCOFID: 25.3 -> 30.6Hurt
Increase layout precision from 0 to 6SceneComposer · OpenLayoutSS Score: .436 -> .558Mixed
Use the any-level model instead of the text-to-image-only baseline (ablation)SceneComposer · OpenLayout-COCO, precision 0CLIP Score: .2473 -> .2496Improved
Use the any-level model instead of the fixed-level layout baseline (ablation)SceneComposer · OpenLayout-COCO, precision 4FID: 36.03 -> 33.70Improved
Use classifier-free guidance with all text feature pyramid levels (ablation)SceneComposer · COCO-stuff valSS Score: .733 -> .736Improved
Randomly permute the order of regional text labels (ablation)SceneComposer · COCO-stuff valFID: 17.20 -> 17.21No clear effect
Randomly permute the order of regional text labels (ablation)SceneComposer · COCO-stuff valmIOU: 23.01 -> 22.76No clear effect
Use SceneComposer rather than VQ-DiffusionCOCO text-to-image generation · COCO valFID: 13.86 -> 8.55Improved

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