Food3D: Text-Driven Customizable 3D Food Generation With Gaussian Splatting

doi:10.1109/TIP.2025.3627408

CSpace

	Food3D: Text-Driven Customizable 3D Food Generation With Gaussian Splatting
	Yu, Dongjian 1; Min, Weiqing 2,3; Jin, Xin 1; Jiang, Qian 1; Yao, Shaowen 1; Jiang, Shuqiang 2,3
	2025
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	34 页码:7290-7304
摘要	Realistic 3D food creation generation plays a critical role in applications such as nutritional assessment, advertising, and virtual content creation. The existing text-to-3D models typically begin by initializing a 3D representation, which is subsequently refined using supervision from a text-to-image model to obtain the final 3D output. In this work, we present Food3D, a novel framework for 3D food generation designed to address two main limitations of current models. First, the limitation of initialization in 3D generation: poor initialization can result in the generated 3D food lacking crucial details and realism, thereby reducing its quality. To address this issue, we propose a generalized method named Food3D-G, which uses Mamba-based initialization to improve the starting point of the initialization process, thereby enhancing the visual fidelity and quality of the generated 3D food. Second, the limitation of text-to-image models: current text-to-3D models often rely on text-to-image models for supervision. However, a considerable gap persists between the generated images and real-world visuals, particularly when modeling complex food structures. These models fail to accurately capture the fine details and textures, which negatively impacts the quality and realism of the generated 3D food models. To address this limitation, we propose a customizable method for personalized 3D food generation, termed Food3D-C. This method employs a dual-branch diffusion model that effectively captures intricate details, particularly in complex food structures. Within the Food3D framework, both proposed methods incorporate 3D Gaussian splatting (3D GS) and a schedulable interval score matching (S-ISM) algorithm to enhance shape and texture generation. Extensive experiments demonstrate that Food3D achieves state-of-the-art performance, with substantial improvements in detail, shape accuracy, and overall visual realism.
关键词	Deep learning diffusion model diffusion model 3D food generation 3D food generation food computing food computing pre-trained model pre-trained model pre-trained model
DOI	10.1109/TIP.2025.3627408
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001615337100004
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/43084
专题	中国科学院计算技术研究所
通讯作者	Jin, Xin
作者单位	1.Yunnan Univ, Sch Software, Kunming 650000, Peoples R China 2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Yu, Dongjian,Min, Weiqing,Jin, Xin,et al. Food3D: Text-Driven Customizable 3D Food Generation With Gaussian Splatting[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2025,34:7290-7304.
APA	Yu, Dongjian,Min, Weiqing,Jin, Xin,Jiang, Qian,Yao, Shaowen,&Jiang, Shuqiang.(2025).Food3D: Text-Driven Customizable 3D Food Generation With Gaussian Splatting.IEEE TRANSACTIONS ON IMAGE PROCESSING,34,7290-7304.
MLA	Yu, Dongjian,et al."Food3D: Text-Driven Customizable 3D Food Generation With Gaussian Splatting".IEEE TRANSACTIONS ON IMAGE PROCESSING 34(2025):7290-7304.