AI Paper Atlas

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

SCP-Diff: Spatial-Categorical Joint Prior for Diffusion Based Semantic Image Synthesis

Huan-ang Gao, Mingju Gao, Jiaju Li, Wenyi Li, Rong Zhi, Hao Tang, Hao Zhao

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 12 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 joint spatial-categorical inference noise prior instead of standard Gaussian noise (ablation)ControlNet · CityscapesFID: 23.35 -> 10.53Improved
add joint prior (ablation)ControlNet · ADE20KmIoU: 20.73 -> 25.61Improved
add spatial prior only (ablation)ControlNet · ADE20KmIoU: 20.73 -> 20.86No clear effect
add spatial prior only (ablation)ControlNet · CityscapesFID: 23.35 -> 12.83Improved
add categorical prior only (ablation)ControlNet · ADE20KAcc: 61.14 -> 66.63Improved
combine spatial and categorical priors into joint prior (ablation)spatial prior · ADE20KFID: 16.03 -> 12.66Improved
apply joint prior to FreestyleNetFreestyleNet · COCO-StuffFID: 14.4 -> 11.3Improved
add joint priorControlNet · ADE20K diversityLPIPS: 0.59 -> 0.56Hurt
use categorical prior only (ablation)ControlNet · Cityscapescolor diversityHurt
choose denoising start fraction mu in [0.8, 0.9] instead of 1 (ablation)SCP-Diff · Cityscapes and ADE20KFIDImproved
increase number of reference images used for priors (ablation)SCP-Diff · ADE20KFIDImproved
select diverse reference images by furthest point sampling in CLIP space (ablation)SCP-Diff · ADE20KFIDImproved

Later papers that compared with this method

1 later accepted paper reports SCP-Diff as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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