NeRF-Texture: Synthesizing Neural Radiance Field Textures

doi:10.1109/TPAMI.2024.3382198

	NeRF-Texture: Synthesizing Neural Radiance Field Textures
	Huang, Yi-Hua 1,2; Cao, Yan-Pei 3; Lai, Yu-Kun 4; Shan, Ying 5; Gao, Lin 1,2
	2024-09-01
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
卷号	46 期号:9 页码:5986-6000
摘要	Texture synthesis is a fundamental problem in computer graphics that would benefit various applications. Existing methods are effective in handling 2D image textures. In contrast, many real-world textures contain meso-structure in the 3D geometry space, such as grass, leaves, and fabrics, which cannot be effectively modeled using only 2D image textures. We propose a novel texture synthesis method with Neural Radiance Fields (NeRF) to capture and synthesize textures from given multi-view images. In the proposed NeRF texture representation, a scene with fine geometric details is disentangled into the meso-structure textures and the underlying base shape. This allows textures with meso-structure to be effectively learned as latent features situated on the base shape, which are fed into a NeRF decoder trained simultaneously to represent the rich view-dependent appearance. Using this implicit representation, we can synthesize NeRF-based textures through patch matching of latent features. However, inconsistencies between the metrics of the reconstructed content space and the latent feature space may compromise the synthesis quality. To enhance matching performance, we further regularize the distribution of latent features by incorporating a clustering constraint. In addition to generating NeRF textures over a planar domain, our method can also synthesize NeRF textures over curved surfaces, which are practically useful. Experimental results and evaluations demonstrate the effectiveness of our approach.
关键词	Shape Rendering (computer graphics) Surface texture Feature extraction Geometry Optimization Image reconstruction Meso-structure texture neural radiance fields texture synthesis
DOI	10.1109/TPAMI.2024.3382198
收录类别	SCI
语种	英语
资助项目	Beijing Municipal Natural Science Foundation for Distinguished Young Scholars[JQ21013] ; National Natural Science Foundation of China[62322210] ; Beijing Municipal Science and Technology Commission[Z231100005923031]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001290498900037
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/39648
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Gao, Lin
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp, Pervas Device, Beijing 100045, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.VAST, Campbell, CA 95008 USA 4.Cardiff Univ, Sch Comp Sci & Informat, Cardiff CF24 4AG, Wales 5.Tencent PCG, ARC Lab, Beijing 100084, Peoples R China
推荐引用方式 GB/T 7714	Huang, Yi-Hua,Cao, Yan-Pei,Lai, Yu-Kun,et al. NeRF-Texture: Synthesizing Neural Radiance Field Textures[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2024,46(9):5986-6000.
APA	Huang, Yi-Hua,Cao, Yan-Pei,Lai, Yu-Kun,Shan, Ying,&Gao, Lin.(2024).NeRF-Texture: Synthesizing Neural Radiance Field Textures.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,46(9),5986-6000.
MLA	Huang, Yi-Hua,et al."NeRF-Texture: Synthesizing Neural Radiance Field Textures".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 46.9(2024):5986-6000.