AI Paper Atlas

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

ST-LDM: A Universal Framework for Text-Grounded Object Generation in Real Images

Xiangtian Xue, Jiasong Wu, Youyong Kong, Lotfi Senhadji, Huazhong Shu

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 1 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
apply deformable feature alignment in stages 2-4 versus no DFA (ablation)ST-LDM multimodal transformer · TOG benchmarkFID: 27.03 -> 6.16Improved
also apply DFA in the initial stage 1 (ablation)ST-LDM · TOG benchmarkFID: 6.16 -> 7.50Hurt
add backward guidance with guidance map (ablation)ST-LDM · TOG benchmarkUserScore: 58.73 -> 89.11Improved
add threshold activation to guidance map (ablation)ST-LDM · TOG benchmarkUserScore: 80.86 -> 89.11Improved
add dilation after activation (ablation)ST-LDM · TOG benchmarkUserScore: 83.98 -> 89.11Improved
add learned 2D offsets in DFA (ablation)DFA · TOG benchmarkIoU: 49.88 -> 65.12Improved
add modulation scalar in DFA (ablation)DFA · TOG benchmarkIoU: 52.49 -> 65.12Improved
combine transformer layer with multi-head cross attention in DFA (ablation)DFA · TOG benchmarkIoU: 28.95 (T-only) / 32.86 (C-only) -> 65.12Improved
add ST-LDM guidance to Stable DiffusionSD V-1.5 · inference timeseconds per image: ~4.1 -> ~6.5 s/imgHurt
use ST-LDM with text only versus GLIGEN with bounding boxestext-grounded object generation · TOG benchmarkFID: 6.24 -> 6.16No clear effect

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