Learning Signed Distance Field for Multi-view Surface Reconstruction

被引:42
|
作者
Zhang, Jingyang [1 ]
Yao, Yao [1 ]
Quan, Long [1 ]
机构
[1] Hong Kong Univ Sci & Technol, Hong Kong, Peoples R China
关键词
STEREO;
D O I
10.1109/ICCV48922.2021.00646
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recent works on implicit neural representations have shown promising results for multi-view surface reconstruction. However, most approaches are limited to relatively simple geometries and usually require clean object masks for reconstructing complex and concave objects. In this work, we introduce a novel neural surface reconstruction framework that leverages the knowledge of stereo matching and feature consistency to optimize the implicit surface representation. More specifically, we apply a signed distance field (SDF) and a surface light field to represent the scene geometry and appearance respectively. The SDF is directly supervised by geometry from stereo matching, and is refined by optimizing the multi-view feature consistency and the fidelity of rendered images. Our method is able to improve the robustness of geometry estimation and support reconstruction of complex scene topologies. Extensive experiments have been conducted on DTU, EPFL and Tanks and Temples datasets. Compared to previous state-of-the-art methods, our method achieves better mesh reconstruction in wide open scenes without masks as input.
引用
收藏
页码:6505 / 6514
页数:10
相关论文
共 50 条
  • [21] Unsupervised Multi-view Learning
    Huang, Ling
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 6442 - 6443
  • [22] Textured mesh surface reconstruction of large buildings with multi-view stereo
    Zhu, Chen
    Leow, Wee Kheng
    VISUAL COMPUTER, 2013, 29 (6-8): : 609 - 615
  • [23] SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration
    Cao, Xu
    Taketomi, Takafumi
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2024, : 20581 - 20590
  • [24] A review on multi-view learning
    Yu, Zhiwen
    Dong, Ziyang
    Yu, Chenchen
    Yang, Kaixiang
    Fan, Ziwei
    Chen, C. L. Philip
    FRONTIERS OF COMPUTER SCIENCE, 2025, 19 (07)
  • [25] Semi-Supervised Multi-View Learning for Gene Network Reconstruction
    Ceci, Michelangelo
    Pio, Gianvito
    Kuzmanovski, Vladimir
    Dzeroski, Saso
    PLOS ONE, 2015, 10 (12):
  • [26] Review of multi-view stereo reconstruction methods based on deep learning
    Yan H.
    Xu F.
    Huang L.
    Liu C.
    Lin C.
    Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2023, 31 (16): : 2444 - 2464
  • [27] Textured mesh surface reconstruction of large buildings with multi-view stereo
    Chen Zhu
    Wee Kheng Leow
    The Visual Computer, 2013, 29 : 609 - 615
  • [28] GenS: Generalizable Neural Surface Reconstruction from Multi-View Images
    Peng, Rui
    Gu, Xiaodong
    Tang, Luyang
    Shen, Shihe
    Yu, Fanqi
    Wang, Ronggang
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [29] Multi-View Reinforcement Learning
    Li, Minne
    Wu, Lisheng
    Ammar, Haitham Bou
    Wang, Jun
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [30] Neural surface reconstruction with saliency-guided sampling in multi-view
    Li, Xiuxiu
    Guo, Yongchen
    Jin, Haiyan
    Zheng, Jiangbin
    IET IMAGE PROCESSING, 2023, 17 (12) : 3411 - 3422