中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
PGT-NeuS: Progressive-Growing Tri-Plane Representation for Neural Surface Reconstruction

文献类型：期刊论文

作者Xiang, Xue-Kun1,2; Yuan, Yu-Jie1,2; Hu, Wen-Bo3; Liu, Yu-Tao1,2; Ma, Yue-Wen3; Gao, Lin1,2
刊名IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
出版日期2025-10-01
卷号31期号:10页码:9213-9224
关键词Image reconstruction Surface reconstruction Neural radiance field Encoding Training Rendering (computer graphics) Accuracy Three-dimensional displays Image color analysis Refining surface reconstruction progressive learning normal priors verification
ISSN号1077-2626
DOI10.1109/TVCG.2025.3590394
英文摘要3D reconstruction from multi-view images is a long-standing problem in computer graphic. Neural 3D reconstruction, especially NeuS and its variants, has improved reconstruction quality compared to traditional methods. However, it is still a challenge for these methods to reconstruct fine-grained geometric details since the spherical harmonic positional encoding lacks the ability to express high-frequency signals. In this paper, we propose a multi-resolution tri-plane feature encoding that leverages the detail reconstruction capabilities of high-resolution tri-plane while using the smoothness of low-resolution tri-plane to suppress high-frequency artifacts. Additionally, a progressive training strategy is introduced, gradually merging scene details from coarse to fine granularity, enhancing reconstruction quality while maintaining training stability and reducing difficulty. Furthermore, to address reconstruction challenges arising from sparse viewpoints and inconsistent lighting in image datasets, we introduce normal priors as supervision and propose consistency verification for multi-view normal priors, which assesses the accuracy of normal priors and effectively supervise the reconstructed surfaces. Moreover, we propose a perturbing and fine-tuning strategy on regions of unreliable normal priors to further improve the quality of geometric surface reconstruction.
资助项目National Natural Science Foundation of China[62322210] ; Beijing Municipal Science and Technology Commission[Z231100005923031] ; Innovation Funding of ICT, CAS[E461020]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001566979000032
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/41716]  
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, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China
3.ByteDance Pico, Beijing 100098, Peoples R China
推荐引用方式
GB/T 7714		 Xiang, Xue-Kun,Yuan, Yu-Jie,Hu, Wen-Bo,et al. PGT-NeuS: Progressive-Growing Tri-Plane Representation for Neural Surface Reconstruction[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2025,31(10):9213-9224.
APA Xiang, Xue-Kun,Yuan, Yu-Jie,Hu, Wen-Bo,Liu, Yu-Tao,Ma, Yue-Wen,&Gao, Lin.(2025).PGT-NeuS: Progressive-Growing Tri-Plane Representation for Neural Surface Reconstruction.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,31(10),9213-9224.
MLA Xiang, Xue-Kun,et al."PGT-NeuS: Progressive-Growing Tri-Plane Representation for Neural Surface Reconstruction".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 31.10(2025):9213-9224.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。