Structured Information for Improving Spatial Relationships in Text-to-Image Generation
Not on the map. Why?
Abstract (arXiv)
Text-to-image (T2I) generation has advanced rapidly, yet faithfully capturing spatial relationships described in natural language prompts remains a major challenge. Prior efforts have addressed this issue through prompt optimization, spatially grounded generation, and semantic refinement. This work introduces a lightweight approach that augments prompts with tuple-based structured information, using a fine-tuned language model for automatic conversion and seamless integration into T2I pipelines. Experimental results demonstrate substantial improvements in spatial accuracy, without compromising overall image quality as measured by Inception Score. Furthermore, the automatically generated tuples exhibit quality comparable to human-crafted tuples. This structured information provides a practical and portable solution to enhance spatial relationships in T2I generation, addressing a key limitation of current large-scale generative systems.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 29 references that are in the map. First posted on arXiv 19 Sep 2025.
Builds on
22 of 29 references.
References · 22
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2025Qwen2.5-VL Technical Reportcited by 5,587
- 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
- 2016Improved Techniques for Training GANscited by 2,970
- 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
- 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
- 2022SpaText: Spatio-Textual Representation for Controllable Image Generationcited by 217
- 2022Optimizing Prompts for Text-to-Image Generationcited by 207
- 2022ReCo: Region-Controlled Text-to-Image Generationcited by 179
- 2023Dense Text-to-Image Generation with Attention Modulationcited by 163
- 2023Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Modelscited by 67
10 more
- 2024PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinementcited by 62
- 2023DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedbackcited by 58
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
- 2021Paint4Poem: A Dataset for Artistic Visualization of Classical Chinese Poemscited by 18
- 2024From Commands to Prompts: LLM-based Semantic File System for AIOScited by 14
- 2022Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue Systemcited by 8
- 2025Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuningcited by 7
- 2024A Generic Method for Fine-grained Category Discovery in Natural Language Textscited by 5
- 2025Using Causality for Enhanced Prediction of Web Traffic Time Seriescited by 4
- 2024Fighting Against the Repetitive Training and Sample Dependency Problem in Few-shot Named Entity Recognitioncited by 3
Built on by
Citing papers per year: 2025: 1.
1 paper.