Salvato in:
Dettagli Bibliografici
Autori principali: Luo, Yucong, Cheng, Mingyue, Ouyang, Jie, Tao, Xiaoyu, Liu, Qi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.18185
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929686125215744
author Luo, Yucong
Cheng, Mingyue
Ouyang, Jie
Tao, Xiaoyu
Liu, Qi
author_facet Luo, Yucong
Cheng, Mingyue
Ouyang, Jie
Tao, Xiaoyu
Liu, Qi
contents Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts. This paper introduces TextMatch, a novel framework that leverages multimodal optimization to address image-text discrepancies in text-to-image (T2I) generation and editing. TextMatch employs a scoring strategy powered by large language models (LLMs) and visual question-answering (VQA) models to evaluate semantic consistency between prompts and generated images. By integrating multimodal in-context learning and chain of thought reasoning, our method dynamically refines prompts through iterative optimization. This process ensures that the generated images better capture user intent of, resulting in higher fidelity and relevance. Extensive experiments demonstrate that TextMatch significantly improves text-image consistency across multiple benchmarks, establishing a reliable framework for advancing the capabilities of text-to-image generative models. Our code is available at https://anonymous.4open.science/r/TextMatch-F55C/.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18185
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TextMatch: Enhancing Image-Text Consistency Through Multimodal Optimization
Luo, Yucong
Cheng, Mingyue
Ouyang, Jie
Tao, Xiaoyu
Liu, Qi
Computer Vision and Pattern Recognition
Artificial Intelligence
Text-to-image generative models excel in creating images from text but struggle with ensuring alignment and consistency between outputs and prompts. This paper introduces TextMatch, a novel framework that leverages multimodal optimization to address image-text discrepancies in text-to-image (T2I) generation and editing. TextMatch employs a scoring strategy powered by large language models (LLMs) and visual question-answering (VQA) models to evaluate semantic consistency between prompts and generated images. By integrating multimodal in-context learning and chain of thought reasoning, our method dynamically refines prompts through iterative optimization. This process ensures that the generated images better capture user intent of, resulting in higher fidelity and relevance. Extensive experiments demonstrate that TextMatch significantly improves text-image consistency across multiple benchmarks, establishing a reliable framework for advancing the capabilities of text-to-image generative models. Our code is available at https://anonymous.4open.science/r/TextMatch-F55C/.
title TextMatch: Enhancing Image-Text Consistency Through Multimodal Optimization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2412.18185