NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions

doi:10.1109/ICCV51070.2023.00386

	NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions
	Zhang Chen 1; Zhong Li 1; Liangchen Song 2; Lele Chen 1; Jingyi Yu3 ; Junsong Yuan 2; Yi Xu 1
	2023-10-06
会议录名称	2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
ISSN	1550-5499
页码	4159-4171
发表状态	已发表
DOI	10.1109/ICCV51070.2023.00386
摘要	We present a novel type of neural fields that uses general radial bases for signal representation. State-of-the-art neural fields typically rely on grid-based representations for storing local neural features and N-dimensional linear kernels for interpolating features at continuous query points. The spatial positions of their neural features are fixed on grid nodes and cannot well adapt to target signals. Our method instead builds upon general radial bases with flexible kernel position and shape, which have higher spatial adaptivity and can more closely fit target signals. To further improve the channel-wise capacity of radial basis functions, we propose to compose them with multi-frequency sinusoid functions. This technique extends a radial basis to multiple Fourier radial bases of different frequency bands without requiring extra parameters, facilitating the representation of details. Moreover, by marrying adaptive radial bases with grid-based ones, our hybrid combination inherits both adaptivity and interpolation smoothness. We carefully designed weighting schemes to let radial bases adapt to different types of signals effectively. Our experiments on 2D image and 3D signed distance field representation demonstrate the higher accuracy and compactness of our method than prior arts. When applied to neural radiance field reconstruction, our method achieves state-of-the-art rendering quality, with small model size and comparable training speed. © 2023 IEEE.
关键词	Training Interpolation Three-dimensional displays Shape Fitting Machine learning Rendering (computer graphics)
会议名称	2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
会议地点	Paris, France
会议日期	1-6 Oct. 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20240915635765
原始文献类型	Conference article (CA)
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/354919
专题	信息科学与技术学院_PI研究组_虞晶怡组
作者单位	1.OPPO US Research Center 2.University at Buffalo 3.ShanghaiTech University
推荐引用方式 GB/T 7714	Zhang Chen,Zhong Li,Liangchen Song,et al. NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions[C]:Institute of Electrical and Electronics Engineers Inc.,2023:4159-4171.