Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liu, Huijie, Wang, Bingcan, Hu, Jie, Wei, Xiaoming, Kang, Guoliang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.09948
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918005657567232
author Liu, Huijie
Wang, Bingcan
Hu, Jie
Wei, Xiaoming
Kang, Guoliang
author_facet Liu, Huijie
Wang, Bingcan
Hu, Jie
Wei, Xiaoming
Kang, Guoliang
contents Dish images play a crucial role in the digital era, with the demand for culturally distinctive dish images continuously increasing due to the digitization of the food industry and e-commerce. In general cases, existing text-to-image generation models excel in producing high-quality images; however, they struggle to capture diverse characteristics and faithful details of specific domains, particularly Chinese dishes. To address this limitation, we propose Omni-Dish, the first text-to-image generation model specifically tailored for Chinese dishes. We develop a comprehensive dish curation pipeline, building the largest dish dataset to date. Additionally, we introduce a recaption strategy and employ a coarse-to-fine training scheme to help the model better learn fine-grained culinary nuances. During inference, we enhance the user's textual input using a pre-constructed high-quality caption library and a large language model, enabling more photorealistic and faithful image generation. Furthermore, to extend our model's capability for dish editing tasks, we propose Concept-Enhanced P2P. Based on this approach, we build a dish editing dataset and train a specialized editing model. Extensive experiments demonstrate the superiority of our methods.
format Preprint
id arxiv_https___arxiv_org_abs_2504_09948
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese Dishes
Liu, Huijie
Wang, Bingcan
Hu, Jie
Wei, Xiaoming
Kang, Guoliang
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
Dish images play a crucial role in the digital era, with the demand for culturally distinctive dish images continuously increasing due to the digitization of the food industry and e-commerce. In general cases, existing text-to-image generation models excel in producing high-quality images; however, they struggle to capture diverse characteristics and faithful details of specific domains, particularly Chinese dishes. To address this limitation, we propose Omni-Dish, the first text-to-image generation model specifically tailored for Chinese dishes. We develop a comprehensive dish curation pipeline, building the largest dish dataset to date. Additionally, we introduce a recaption strategy and employ a coarse-to-fine training scheme to help the model better learn fine-grained culinary nuances. During inference, we enhance the user's textual input using a pre-constructed high-quality caption library and a large language model, enabling more photorealistic and faithful image generation. Furthermore, to extend our model's capability for dish editing tasks, we propose Concept-Enhanced P2P. Based on this approach, we build a dish editing dataset and train a specialized editing model. Extensive experiments demonstrate the superiority of our methods.
title Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese Dishes
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
url https://arxiv.org/abs/2504.09948