Asteroid-NeRF: A deep-learning method for 3D surface reconstruction of asteroids

被引:0
|
作者
Chen, Shihan [1 ]
Wu, Bo [1 ]
Li, Hongliang [1 ]
Li, Zhaojin [1 ]
Liu, Yi [1 ]
机构
[1] Hong Kong Polytech Univ, Res Ctr Deep Space Explorat, Dept Land Surveying & Geoinformat, Hung Hom,Kowloon, Hong Kong, Peoples R China
关键词
techniques: image processing; minor planets; asteroids:; general; planets and satellites: surfaces; SHAPE; STEREOPHOTOCLINOMETRY; TOPOGRAPHY; ITOKAWA; ALBEDO; IMAGES; MASS;
D O I
10.1051/0004-6361/202450053
中图分类号
P1 [天文学];
学科分类号
0704 ;
摘要
Context. Asteroids preserve important information about the origin and evolution of the Solar System. Three-dimensional (3D) surface models of asteroids are essential for exploration missions and scientific research. Regular methods for 3D surface reconstruction of asteroids, such as stereo-photogrammetry (SPG), usually struggle to reconstruct textureless areas and can only generate sparse surface models. Stereo-photoclinometry (SPC) can reconstruct pixel-wise topographic details but its performance depends on the availability of images obtained under different illumination conditions and suffers from uncertainties related to surface reflectance and albedo. Aims. This paper presents Asteroid-NeRF, a novel deep-learning method for 3D surface reconstruction of asteroids that is based on the state-of-the-art neural radiance field (NeRF) method. Methods. Asteroid-NeRF uses a signed distance field (SDF) to reconstruct a 3D surface model from multi-view posed images of an asteroid. In addition, Asteroid-NeRF incorporates appearance embedding to adapt to different illumination conditions and to maintain the geometric consistency of a reconstructed surface, allowing it to deal with the different solar angles and exposure conditions commonly seen in asteroid images. Moreover, Asteroid-NeRF incorporates multi-view photometric consistency to constrain the SDF, enabling optimised reconstruction. Results. Experimental evaluations using actual images of asteroids Itokawa and Bennu demonstrate the promising performance of Asteroid-NeRF, complementing traditional methods such as SPG and SPC. Furthermore, due to the global consistency and pixel-wise training of Asteroid-NeRF, it produces highly detailed surface reconstructions. Asteroid-NeRF offers a new and effective solution for high-resolution 3D surface reconstruction of asteroids that will aid future exploratory missions and scientific research on asteroids.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] NeRF FOR HERITAGE 3D RECONSTRUCTION
    Mazzacca, G.
    Karami, A.
    Rigon, S.
    Farella, E. M.
    Trybala, P.
    Remondino, F.
    29TH CIPA SYMPOSIUM DOCUMENTING, UNDERSTANDING, PRESERVING CULTURAL HERITAGE. HUMANITIES AND DIGITAL TECHNOLOGIES FOR SHAPING THE FUTURE, VOL. 48-M-2, 2023, : 1051 - 1058
  • [2] Urban object classification with 3D Deep-Learning
    Zegaoui, Younes
    Chaumont, Marc
    Subsol, Gerard
    Borianne, Philippe
    Derras, Mustapha
    2019 JOINT URBAN REMOTE SENSING EVENT (JURSE), 2019,
  • [3] DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstruction
    Cruz, Rodrigo Santa
    Lebrat, Leo
    Bourgeat, Pierrick
    Fookes, Clinton
    Fripp, Jurgen
    Salvado, Olivier
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2021), 2021, : 806 - 815
  • [4] DPPS: A deep-learning based point-light photometric stereo method for 3D reconstruction of metallic surfaces
    Yang, Ru
    Wang, Yaoke
    Liao, Shuheng
    Guo, Ping
    MEASUREMENT, 2023, 210
  • [5] Fast Data Generation for Training Deep-Learning 3D Reconstruction Approaches for Camera Arrays
    Barrios, Theo
    Prevost, Stephanie
    Loscos, Celine
    JOURNAL OF IMAGING, 2024, 10 (01)
  • [6] A Freehand 3D Ultrasound Reconstruction Method Based on Deep Learning
    Chen, Xin
    Chen, Houjin
    Peng, Yahui
    Liu, Liu
    Huang, Chang
    ELECTRONICS, 2023, 12 (07)
  • [7] Steel surface defect detection based on deep learning 3D reconstruction
    Lan H.
    Yu J.-B.
    Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2023, 57 (03): : 466 - 476+561
  • [8] A deep-learning approach to the 3D reconstruction of dust density and temperature in star-forming regions
    Ksoll, Victor F.
    Reissl, Stefan
    Klessen, Ralf S.
    Stephens, Ian W.
    Smith, Rowan J.
    Soler, Juan D.
    Traficante, Alessio
    Girichidis, Philipp
    Testi, Leonardo
    Hennebelle, Patrick
    Molinari, Sergio
    ASTRONOMY & ASTROPHYSICS, 2024, 683
  • [9] Unsupervised 3D seismic data reconstruction using a weighted-attentive deep-learning framework
    Chen, Gui
    Liu, Yang
    Sun, Yuhang
    GEOPHYSICS, 2024, 89 (06) : V635 - V652
  • [10] A New 3D Surface Reconstruction Method
    Fu, Wei
    Wu, Lushen
    5TH ANNUAL INTERNATIONAL CONFERENCE ON INFORMATION SYSTEM AND ARTIFICIAL INTELLIGENCE (ISAI2020), 2020, 1575