多模态条件3D面部几何生成

IF 2.8 4区计算机科学 Q2 COMPUTER SCIENCE, SOFTWARE ENGINEERING

Computers & Graphics-Uk Pub Date : 2025-08-13 DOI:10.1016/j.cag.2025.104325

Christopher Otto , Prashanth Chandran , Sebastian Weiss , Markus Gross , Gaspard Zoss , Derek Bradley

{"title":"多模态条件3D面部几何生成","authors":"Christopher Otto , Prashanth Chandran , Sebastian Weiss , Markus Gross , Gaspard Zoss , Derek Bradley","doi":"10.1016/j.cag.2025.104325","DOIUrl":null,"url":null,"abstract":"<div><div>We present a new method for multimodal conditional 3D face geometry generation that allows user-friendly control over the output identity and expression via a number of different conditioning signals. Within a single model, we demonstrate 3D faces generated from artistic sketches, portrait photos, Canny edges, FLAME face model parameters, 2D face landmarks, or text prompts. Our approach is based on a diffusion process that generates 3D geometry in a 2D parameterized UV domain. Geometry generation passes each conditioning signal through a set of cross-attention layers (IP-Adapter), one set for each user-defined conditioning signal. The result is an easy-to-use 3D face generation tool that produces topology-consistent, high-quality geometry with fine-grain user control.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"132 ","pages":"Article 104325"},"PeriodicalIF":2.8000,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multimodal Conditional 3D Face Geometry Generation\",\"authors\":\"Christopher Otto , Prashanth Chandran , Sebastian Weiss , Markus Gross , Gaspard Zoss , Derek Bradley\",\"doi\":\"10.1016/j.cag.2025.104325\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>We present a new method for multimodal conditional 3D face geometry generation that allows user-friendly control over the output identity and expression via a number of different conditioning signals. Within a single model, we demonstrate 3D faces generated from artistic sketches, portrait photos, Canny edges, FLAME face model parameters, 2D face landmarks, or text prompts. Our approach is based on a diffusion process that generates 3D geometry in a 2D parameterized UV domain. Geometry generation passes each conditioning signal through a set of cross-attention layers (IP-Adapter), one set for each user-defined conditioning signal. The result is an easy-to-use 3D face generation tool that produces topology-consistent, high-quality geometry with fine-grain user control.</div></div>\",\"PeriodicalId\":50628,\"journal\":{\"name\":\"Computers & Graphics-Uk\",\"volume\":\"132 \",\"pages\":\"Article 104325\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2025-08-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers & Graphics-Uk\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0097849325001669\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers & Graphics-Uk","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0097849325001669","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}

引用次数: 0

摘要

我们提出了一种多模态条件三维人脸几何生成的新方法，该方法允许用户通过许多不同的条件信号对输出身份和表达进行用户友好控制。在单个模型中，我们演示了从艺术草图、肖像照片、Canny边缘、FLAME面部模型参数、2D面部地标或文本提示生成的3D面部。我们的方法是基于在2D参数化UV域中生成3D几何的扩散过程。几何生成通过一组交叉注意层（IP-Adapter）传递每个调节信号，一组用于每个用户定义的调节信号。结果是一个易于使用的3D面部生成工具，可以产生拓扑一致的高质量几何形状，并具有精细的用户控制。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Multimodal Conditional 3D Face Geometry Generation

We present a new method for multimodal conditional 3D face geometry generation that allows user-friendly control over the output identity and expression via a number of different conditioning signals. Within a single model, we demonstrate 3D faces generated from artistic sketches, portrait photos, Canny edges, FLAME face model parameters, 2D face landmarks, or text prompts. Our approach is based on a diffusion process that generates 3D geometry in a 2D parameterized UV domain. Geometry generation passes each conditioning signal through a set of cross-attention layers (IP-Adapter), one set for each user-defined conditioning signal. The result is an easy-to-use 3D face generation tool that produces topology-consistent, high-quality geometry with fine-grain user control.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Computers & Graphics-Uk 工程技术-计算机：软件工程

CiteScore

5.30

自引率

12.00%

发文量

173

审稿时长

38 days

期刊介绍： Computers & Graphics is dedicated to disseminate information on research and applications of computer graphics (CG) techniques. The journal encourages articles on: 1. Research and applications of interactive computer graphics. We are particularly interested in novel interaction techniques and applications of CG to problem domains. 2. State-of-the-art papers on late-breaking, cutting-edge research on CG. 3. Information on innovative uses of graphics principles and technologies. 4. Tutorial papers on both teaching CG principles and innovative uses of CG in education.