AI Paper Atlas

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

BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

Jinheng Xie, Yuexiang Li, Yawen Huang, Haozhe Liu, Wentian Zhang, Yefeng Zheng, Mike Zheng Shou

ICCV 2023 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 221 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 outer-box constraint to inner-box constraint (ablation)BoxDiff · box-conditioned synthesisYOLO AP: 9.8 -> 20.2Improved
add corner constraint (ablation)BoxDiff (IB+OB) · box-conditioned synthesisYOLO AP: 20.2 -> 22.3Improved
use topk sampling instead of all elements (ablation)BoxDiff · box-conditioned synthesisT2I-Sim: AP 24.8 -> 22.3; T2I-Sim 0.3489 -> 0.3513Mixed
random sampling instead of topk (ablation)BoxDiff · box-conditioned synthesisYOLO AP: 22.3 -> 21.4Hurt
remove sample() from corner constraint (ablation)BoxDiff · box-conditioned synthesisYOLO AP: 22.3 -> 7.7Hurt
add BoxDiff constraints to Stable DiffusionStable Diffusion · box-conditioned synthesisYOLO AP: 2.8 -> 22.3Improved
plug BoxDiff into GLIGENGLIGEN · box-conditioned synthesisYOLO AP: 29.7 -> 40.2Improved
give BoxDiff uncommon object combinations or locationsBoxDiff · unusual promptsqualitativeHurt

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