AI Paper Atlas

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

Textual-Visual Logic Challenge: Understanding and Reasoning in Text-to-Image Generation

Peixi Xiong, Michael A Kozuch, Nilesh Jain

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 2 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 Negative Pair Discriminator loss (Focal Informative) (ablation)proposed T2I model · TV-LogicRSIM: 69.91 -> 72.78Improved
add learned relation attention (Focal Relation) (ablation)proposed T2I model · TV-LogicRSIM: 66.12 -> 72.78Improved
add Cross-Modality Tower instead of direct concatenation (ablation)proposed T2I model · TV-LogicRSIM: 68.90 -> 72.78Improved
add learned relation attention (Focal Relation) (ablation)proposed T2I model · TV-LogicFID: 39.41 -> 40.60Hurt
proposed model versus strongest baseline LatteGANTV-Logic · TV-LogicRSIM: 63.03 -> 72.78Improved
numerical representation promptsall models · TV-Logic Numerical RepF1: Ours 62.12 vs Detail category 86.79Hurt
scenarios with multiple same-attribute entities or target identificationall models · TV-Logic ambiguity categoriesRSIM: Ours 81.01 (Detail) -> 58.04 (Relational Ambiguity)Hurt

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