Zhenwei Wang, Tengfei Wang, Zexin He, Gerhard Hancke, Ziwei Liu, Rynson W. H. Lau
{"title":"菲迪亚斯利用参考增强扩散从文本、图像和三维条件创建三维内容的生成模型","authors":"Zhenwei Wang, Tengfei Wang, Zexin He, Gerhard Hancke, Ziwei Liu, Rynson W. H. Lau","doi":"arxiv-2409.11406","DOIUrl":null,"url":null,"abstract":"In 3D modeling, designers often use an existing 3D model as a reference to\ncreate new ones. This practice has inspired the development of Phidias, a novel\ngenerative model that uses diffusion for reference-augmented 3D generation.\nGiven an image, our method leverages a retrieved or user-provided 3D reference\nmodel to guide the generation process, thereby enhancing the generation\nquality, generalization ability, and controllability. Our model integrates\nthree key components: 1) meta-ControlNet that dynamically modulates the\nconditioning strength, 2) dynamic reference routing that mitigates misalignment\nbetween the input image and 3D reference, and 3) self-reference augmentations\nthat enable self-supervised training with a progressive curriculum.\nCollectively, these designs result in a clear improvement over existing\nmethods. Phidias establishes a unified framework for 3D generation using text,\nimage, and 3D conditions with versatile applications.","PeriodicalId":501130,"journal":{"name":"arXiv - CS - Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion\",\"authors\":\"Zhenwei Wang, Tengfei Wang, Zexin He, Gerhard Hancke, Ziwei Liu, Rynson W. H. Lau\",\"doi\":\"arxiv-2409.11406\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In 3D modeling, designers often use an existing 3D model as a reference to\\ncreate new ones. This practice has inspired the development of Phidias, a novel\\ngenerative model that uses diffusion for reference-augmented 3D generation.\\nGiven an image, our method leverages a retrieved or user-provided 3D reference\\nmodel to guide the generation process, thereby enhancing the generation\\nquality, generalization ability, and controllability. Our model integrates\\nthree key components: 1) meta-ControlNet that dynamically modulates the\\nconditioning strength, 2) dynamic reference routing that mitigates misalignment\\nbetween the input image and 3D reference, and 3) self-reference augmentations\\nthat enable self-supervised training with a progressive curriculum.\\nCollectively, these designs result in a clear improvement over existing\\nmethods. Phidias establishes a unified framework for 3D generation using text,\\nimage, and 3D conditions with versatile applications.\",\"PeriodicalId\":501130,\"journal\":{\"name\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.11406\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.11406","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
In 3D modeling, designers often use an existing 3D model as a reference to
create new ones. This practice has inspired the development of Phidias, a novel
generative model that uses diffusion for reference-augmented 3D generation.
Given an image, our method leverages a retrieved or user-provided 3D reference
model to guide the generation process, thereby enhancing the generation
quality, generalization ability, and controllability. Our model integrates
three key components: 1) meta-ControlNet that dynamically modulates the
conditioning strength, 2) dynamic reference routing that mitigates misalignment
between the input image and 3D reference, and 3) self-reference augmentations
that enable self-supervised training with a progressive curriculum.
Collectively, these designs result in a clear improvement over existing
methods. Phidias establishes a unified framework for 3D generation using text,
image, and 3D conditions with versatile applications.