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
  • [41] Overview of Multi-View 3D Reconstruction Techniques in Deep Learning
    Wang, Wenju
    Tang, Bang
    Gu, Zehua
    Wang, Sen
    Computer Engineering and Applications, 2025, 61 (06) : 22 - 35
  • [42] Multi-View Video Representation Based on Fast Monte Carlo Surface Reconstruction
    Salvador, Jordi
    Casas, Josep R.
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (09) : 3342 - 3352
  • [43] Accurate multi-view reconstruction using robust binocular stereo and surface meshing
    Bradley, Derek
    Boubekeur, Tamy
    Heidrich, Wolfgang
    2008 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-12, 2008, : 3498 - +
  • [44] Improving Neural Surface Reconstruction with Feature Priors from Multi-view Images
    Ren, Xinlin
    Cao, Chenjie
    Fu, Yanwei
    Xu, Xiangyang
    COMPUTER VISION - ECCV 2024, PT LVIII, 2025, 15116 : 445 - 463
  • [45] Deep graph reconstruction for multi-view clustering
    Zhao, Mingyu
    Yang, Weidong
    Nie, Feiping
    NEURAL NETWORKS, 2023, 168 : 560 - 568
  • [46] JOINT RECONSTRUCTION OF COMPRESSED MULTI-VIEW IMAGES
    Chen, Xu
    Frossard, Pascal
    2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 1005 - +
  • [47] MULTI-VIEW FRAME RECONSTRUCTION WITH CONDITIONAL GAN
    Mahmud, Tahmida
    Billah, Mohammad
    Roy-Chowdhury, Amit K.
    2018 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2018), 2018, : 1164 - 1168
  • [48] Multi-view Clustering Based on Collaborative Reconstruction
    Zhou, Kailing
    Jia, Hong
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, PT I, ICIC 2024, 2024, 14875 : 315 - 327
  • [49] Ensemble multi-view feature set partitioning method for effective multi-view learning
    Singh, Ritika
    Kumar, Vipin
    KNOWLEDGE AND INFORMATION SYSTEMS, 2024, 66 (08) : 4957 - 5001
  • [50] Compressed Multi-view Imaging with Joint Reconstruction
    Fu, Changjun
    Ji, Xiangyang
    Dai, Qionghai
    2011 DATA COMPRESSION CONFERENCE (DCC), 2011, : 448 - 448