HSDF: Hybrid Sign and Distance Field for Neural Representation of Surfaces With Arbitrary Topologies

doi:10.1109/TVCG.2024.3443508

	HSDF: Hybrid Sign and Distance Field for Neural Representation of Surfaces With Arbitrary Topologies
	Wang, Li 1,2; Liu, Yu-Tao 1,2; Yang, Jie 1; Chen, Weikai 3; Meng, Xiaoxu 3; Yang, Bo 3; Li, Jintao 1,2; Gao, Lin 1,2
	2025-09-01
发表期刊	IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
ISSN	1077-2626
卷号	31 期号:9 页码:5215-5228
摘要	Neural implicit function based on signed distance field (SDF) has achieved impressive progress in reconstructing 3D models with high fidelity. However, such approaches can only represent closed surfaces. Recent works based on unsigned distance function (UDF) are proposed to handle both watertight and single-layered open surfaces. Nonetheless, as UDF is signless, its direct output is limited to the point cloud, which imposes an additional challenge on extracting high-quality meshes from discrete points. To address this challenge, we present a novel neural implicit representation coded HSDF, which is a hybrid of signed and unsigned distance fields. In particular, HSDF is able to represent arbitrary topologies containing both closed and open surfaces while being compatible with existing iso-surface extraction techniques for easy field-to-mesh conversion. In addition to predicting a UDF, we propose to learn an additional sign field. Unlike traditional SDF, HSDF is able to locate the surface of interest before level surface extraction by generating surface points following NDF (Chibane et al. 2020). We are then able to obtain open surfaces via an adaptive meshing approach that only instantiates regions containing surfaces into a polygon mesh. HSDF benefits downstream tasks like neural rendering, as it enables the rendering of back-faces of open surfaces. We also propose HSDF-Net, a dedicated learning framework that factorizes the learning of HSDF into two easier sub-problems. Experiments and evaluations show that HSDF outperforms the state-of-the-art techniques both qualitatively and quantitatively on some of the used datasets.
关键词	Shape Surface reconstruction Three-dimensional displays Rendering (computer graphics) Topology Surface treatment Geometry Implicit field point cloud reconstruction signed distance field unsigned distance field
DOI	10.1109/TVCG.2024.3443508
收录类别	SCI
语种	英语
资助项目	CCF-Tencent Open Fund ; Beijing Municipal Natural Science Foundation for Distinguished Young Scholars[JQ21013] ; National Natural Science Foundation of China[62322210] ; National Natural Science Foundation of China[62061136007] ; National Natural Science Foundation of China[61872440] ; Royal Society Newton Advanced Fellowship[NAF\R2\192151] ; Youth Innovation Promotion Association CAS
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001542452400043
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/2XEOYT63/41987
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 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Tencent Games, DCC Algorithm Res Ctr, Los Angeles, CA 90066 USA
推荐引用方式 GB/T 7714	Wang, Li,Liu, Yu-Tao,Yang, Jie,et al. HSDF: Hybrid Sign and Distance Field for Neural Representation of Surfaces With Arbitrary Topologies[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2025,31(9):5215-5228.
APA	Wang, Li.,Liu, Yu-Tao.,Yang, Jie.,Chen, Weikai.,Meng, Xiaoxu.,...&Gao, Lin.(2025).HSDF: Hybrid Sign and Distance Field for Neural Representation of Surfaces With Arbitrary Topologies.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,31(9),5215-5228.
MLA	Wang, Li,et al."HSDF: Hybrid Sign and Distance Field for Neural Representation of Surfaces With Arbitrary Topologies".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 31.9(2025):5215-5228.