Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation

doi:10.1111/cgf.14981

	Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation
	Liu, Ruiyang1,2 ; Xiang, Jinxu 1; Zhao, Bowen 1; Zhang, Ran 1; Yu, Jingyi2 ; Zheng, Changxi 1
	2023-10
发表期刊	COMPUTER GRAPHICS FORUM (IF:2.7[JCR-2023],2.9[5-Year])
ISSN	0167-7055
EISSN	1467-8659
卷号	42 期号:7
DOI	10.1111/cgf.14981
摘要	Neural Radiance Fields (NeRF) have significantly advanced the generation of highly realistic and expressive 3D scenes. However, the task of editing NeRF, particularly in terms of geometry modification, poses a significant challenge. This issue has obstructed NeRF's wider adoption across various applications. To tackle the problem of efficiently editing neural implicit fields, we introduce Neural Impostor, a hybrid representation incorporating an explicit tetrahedral mesh alongside a multigrid implicit field designated for each tetrahedron within the explicit mesh. Our framework bridges the explicit shape manipulation and the geometric editing of implicit fields by utilizing multigrid barycentric coordinate encoding, thus offering a pragmatic solution to deform, composite, and generate neural implicit fields while maintaining a complex volumetric appearance. Furthermore, we propose a comprehensive pipeline for editing neural implicit fields based on a set of explicit geometric editing operations. We show the robustness and adaptability of our system through diverse examples and experiments, including the editing of both synthetic objects and real captured data. Finally, we demonstrate the authoring process of a hybrid synthetic-captured object utilizing a variety of editing operations, underlining the transformative potential of Neural Impostor in the field of 3D content creation and manipulation. © 2023 Eurographics - The European Association for Computer Graphics and John Wiley & Sons Ltd.
关键词	Mesh generation Textures 3D scenes Appearance and texture representation CCS concept Computing methodologies Editing operations Image-Based Rendering Multigrids Shape manipulation Texture representation • computing methodology → rendering
URL	查看原文
收录类别	EI
语种	英语
出版者	John Wiley and Sons Inc
EI入藏号	20234715079713
EI主题词	Rendering (computer graphics)
EI分类号	723.2 Data Processing and Image Processing ; 723.5 Computer Applications ; 921.4 Combinatorial Mathematics, Includes Graph Theory, Set Theory
原始文献类型	Journal article (JA)
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/347907
专题	信息科学与技术学院_博士生信息科学与技术学院_PI研究组_虞晶怡组
通讯作者	Zhang, Ran
作者单位	1.Tencent Pixel Lab, United States; 2.ShanghaiTech University, China
第一作者单位	上海科技大学
推荐引用方式 GB/T 7714	Liu, Ruiyang,Xiang, Jinxu,Zhao, Bowen,et al. Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation[J]. COMPUTER GRAPHICS FORUM,2023,42(7).
APA	Liu, Ruiyang,Xiang, Jinxu,Zhao, Bowen,Zhang, Ran,Yu, Jingyi,&Zheng, Changxi.(2023).Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation.COMPUTER GRAPHICS FORUM,42(7).
MLA	Liu, Ruiyang,et al."Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation".COMPUTER GRAPHICS FORUM 42.7(2023).