Salvato in:
Dettagli Bibliografici
Autori principali: Schildermans, Sander, Tian, Chang, Jiao, Ying, Moens, Marie-Francine
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.15962
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918144369491968
author Schildermans, Sander
Tian, Chang
Jiao, Ying
Moens, Marie-Francine
author_facet Schildermans, Sander
Tian, Chang
Jiao, Ying
Moens, Marie-Francine
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_15962
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structured Information for Improving Spatial Relationships in Text-to-Image Generation
Schildermans, Sander
Tian, Chang
Jiao, Ying
Moens, Marie-Francine
Artificial Intelligence
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.
title Structured Information for Improving Spatial Relationships in Text-to-Image Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2509.15962