Food3D: Text-Driven Customizable 3D Food Generation With Gaussian Splatting
文献类型：期刊论文
| 作者 | Yu, Dongjian2; Min, Weiqing1,3; Jin, Xin2; Jiang, Qian2; Yao, Shaowen2; Jiang, Shuqiang1,3 |
| 刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING
 |
| 出版日期 | 2025 |
| 卷号 | 34页码:7290-7304 |
| 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 |
| ISSN号 | 1057-7149 |
| DOI | 10.1109/TIP.2025.3627408 |
| 英文摘要 | 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. |
| 资助项目 | Yunnan Fundamental Research Projects[202503AG380006] ; Yunnan Fundamental Research Projects[202301AW070007] ; Yunnan Fundamental Research Projects[202301AU070210] ; Yunnan Fundamental Research Projects[202401AT070470] ; Graduate Research Innovation Project of Yunnan University[ZC-24248562] ; Graduate Research Innovation Project of Yunnan University[KC-252511698] ; Yunnan Province Expert Workstations[202305AF150078] ; National Natural Science Foundation of China[10.13039/501100001809] ; National Natural Science Foundation of China[62261060] ; National Natural Science Foundation of China[62125207] ; Yunnan Province Special Project[202403AP140021] ; Xingdian Talent Project in Yunnan Province of China ; Beijing Natural Science Foundation[JQ24021] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001615337100004 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/43083]  |
| 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.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Yunnan Univ, Sch Software, Kunming 650000, 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. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。