Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916857698582528 |
|---|---|
| author | Izadi, Amir Mohammad Hosseini, Seyed Mohammad Hadi Tabar, Soroush Vafaie Abdollahi, Ali Saghafian, Armin Baghshah, Mahdieh Soleymani |
| author_facet | Izadi, Amir Mohammad Hosseini, Seyed Mohammad Hadi Tabar, Soroush Vafaie Abdollahi, Ali Saghafian, Armin Baghshah, Mahdieh Soleymani |
| contents | Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a formidable challenge. In response, we present an innovative, training-free method that directly addresses these challenges by incorporating tailored objectives to account for textual constraints. Unlike layout-based approaches that enforce rigid structures and limit diversity, our proposed approach offers a more flexible arrangement of the scene by imposing just the extracted constraints from the text, without any unnecessary additions. These constraints are formulated as losses-entity missing, entity mixing, attribute binding, and spatial relationships-integrated into a unified loss that is applied in the first generation stage. Furthermore, we introduce a feedback-driven system for fine-grained initial noise refinement. This system integrates a verifier that evaluates the generated image, identifies inconsistencies, and provides corrective feedback. Leveraging this feedback, our refinement method first targets the unmet constraints by refining the faulty attention maps caused by initial noise, through the optimization of selective losses associated with these constraints. Subsequently, our unified loss function is reapplied to proceed the second generation phase. Experimental results demonstrate that our method, relying solely on our proposed objective functions, significantly enhances compositionality, achieving a 24% improvement in human evaluation and a 25% gain in spatial relationships. Furthermore, our fine-grained noise refinement proves effective, boosting performance by up to 5%. Code is available at \href{https://github.com/hadi-hosseini/noise-refinement}{https://github.com/hadi-hosseini/noise-refinement}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06506 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation Izadi, Amir Mohammad Hosseini, Seyed Mohammad Hadi Tabar, Soroush Vafaie Abdollahi, Ali Saghafian, Armin Baghshah, Mahdieh Soleymani Computer Vision and Pattern Recognition Machine Learning Text-to-image generative models have made significant advancements in recent years; however, accurately capturing intricate details in textual prompts-such as entity missing, attribute binding errors, and incorrect relationships remains a formidable challenge. In response, we present an innovative, training-free method that directly addresses these challenges by incorporating tailored objectives to account for textual constraints. Unlike layout-based approaches that enforce rigid structures and limit diversity, our proposed approach offers a more flexible arrangement of the scene by imposing just the extracted constraints from the text, without any unnecessary additions. These constraints are formulated as losses-entity missing, entity mixing, attribute binding, and spatial relationships-integrated into a unified loss that is applied in the first generation stage. Furthermore, we introduce a feedback-driven system for fine-grained initial noise refinement. This system integrates a verifier that evaluates the generated image, identifies inconsistencies, and provides corrective feedback. Leveraging this feedback, our refinement method first targets the unmet constraints by refining the faulty attention maps caused by initial noise, through the optimization of selective losses associated with these constraints. Subsequently, our unified loss function is reapplied to proceed the second generation phase. Experimental results demonstrate that our method, relying solely on our proposed objective functions, significantly enhances compositionality, achieving a 24% improvement in human evaluation and a 25% gain in spatial relationships. Furthermore, our fine-grained noise refinement proves effective, boosting performance by up to 5%. Code is available at \href{https://github.com/hadi-hosseini/noise-refinement}{https://github.com/hadi-hosseini/noise-refinement}. |
| title | Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.06506 |