Twin Co-Adaptive Dialogue for Progressive 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_ | 1866908851403489280 |
|---|---|
| author | Wang, Jianhui He, Yangfan Zhong, Yan Song, Xinyuan Su, Jiayi Feng, Yuheng Wang, Ruoyu He, Hongyang Zhu, Wenyu Yuan, Xinhang Zhang, Miao Li, Keqin Chen, Jiaqi Shi, Tianyu Wang, Xueqian |
| author_facet | Wang, Jianhui He, Yangfan Zhong, Yan Song, Xinyuan Su, Jiayi Feng, Yuheng Wang, Ruoyu He, Hongyang Zhu, Wenyu Yuan, Xinhang Zhang, Miao Li, Keqin Chen, Jiaqi Shi, Tianyu Wang, Xueqian |
| contents | Modern text-to-image generation systems have enabled the creation of remarkably realistic and high-quality visuals, yet they often falter when handling the inherent ambiguities in user prompts. In this work, we present Twin-Co, a framework that leverages synchronized, co-adaptive dialogue to progressively refine image generation. Instead of a static generation process, Twin-Co employs a dynamic, iterative workflow where an intelligent dialogue agent continuously interacts with the user. Initially, a base image is generated from the user's prompt. Then, through a series of synchronized dialogue exchanges, the system adapts and optimizes the image according to evolving user feedback. The co-adaptive process allows the system to progressively narrow down ambiguities and better align with user intent. Experiments demonstrate that Twin-Co not only enhances user experience by reducing trial-and-error iterations but also improves the quality of the generated images, streamlining creative process across various applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_14868 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Twin Co-Adaptive Dialogue for Progressive Image Generation Wang, Jianhui He, Yangfan Zhong, Yan Song, Xinyuan Su, Jiayi Feng, Yuheng Wang, Ruoyu He, Hongyang Zhu, Wenyu Yuan, Xinhang Zhang, Miao Li, Keqin Chen, Jiaqi Shi, Tianyu Wang, Xueqian Computer Vision and Pattern Recognition Modern text-to-image generation systems have enabled the creation of remarkably realistic and high-quality visuals, yet they often falter when handling the inherent ambiguities in user prompts. In this work, we present Twin-Co, a framework that leverages synchronized, co-adaptive dialogue to progressively refine image generation. Instead of a static generation process, Twin-Co employs a dynamic, iterative workflow where an intelligent dialogue agent continuously interacts with the user. Initially, a base image is generated from the user's prompt. Then, through a series of synchronized dialogue exchanges, the system adapts and optimizes the image according to evolving user feedback. The co-adaptive process allows the system to progressively narrow down ambiguities and better align with user intent. Experiments demonstrate that Twin-Co not only enhances user experience by reducing trial-and-error iterations but also improves the quality of the generated images, streamlining creative process across various applications. |
| title | Twin Co-Adaptive Dialogue for Progressive Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.14868 |