Research on 3D Object Reconstruction Method based on Deep Learning
DOI:
https://doi.org/10.54097/hset.v39i.6732Keywords:
3D Reconstruction; Theory of Multi-view Geometry; Point Cloud; Voxel; Grid.Abstract
3D reconstruction is a classic task in the field of computer graphics. More and more researchers try to replicate the success of deep learning in 2D image processing tasks to 3D reconstruction tasks, so 3D reconstruction related research based on deep learning has gradually become a research hotspot. Compared with the traditional 3D reconstruction methods that require precision acquisition equipment and strict calibration of image information, the 3D reconstruction method based on deep learning completes the matching of 2D images to 3D models through deep neural networks, and can reconstruct 3D models of various categories of objects from RGB images obtained by ordinary acquisition equipment in a large number and quickly. This paper introduces the state of the art of 3D voxel reconstruction, 3D points cloud reconstruction and 3D mesh reconstruction, respectively. According to the different representation methods of 3D objects, the 3D object reconstruction methods based on deep learning are classified and reviewed, the characteristics and shortcomings of existing methods are analyzed, and three important research trends are summarized.
Downloads
References
Fangfang. Research on power load forecasting based on Improved BP neural network. Harbin Institute of Technology, 2011.
William E. Lorensen, Harvey E. Cline. Marching cubes: A high resolution 3D surface construction algorithm. Acm sig-graph computer graphics, 1987, 21(4), 1-11.
YU Qian, LU Jinxiao, BAI Jiquan, Fan Honghui. Review of three-dimensional object reconstruction methods based on deep learning. Journal of Jiangsu Institute of Technology, 2022, 28(04):31-41.
He Xiao, Zhu Mingrui, et al. BiTGAN: bilateral generative adversarial networks for Chinese ink wash painting style transfer. Science China Information Sciences, 2022,66(1): 239-248.
Mahad Fairuz Safwan, et al. Learning Pyramidal Feature Hierarchy for 3D Reconstruction. IEICE Transactions on Information and Systems, 2022, E105. D (2).
Yang G D, Cui Y, Belongie S, et al. Learning single view 3D reconstruction with limited pose supervision, European Conference on Computer Vision, 2018, 2018:90-105.
Peng S Y, Niemeyer M, Mescheder L, et al. Convolutional occupancy networks, European Conference on Computer Vision, 2020: 523-540.
Liu S L, Guo H X, Pan H, et al. Deep implicit moving least- squares functions for 3D reconstruction, 2021 Conference on Computer Vision and Pattern Recognition, 2021:1788-1797.
Wang P S, Liu Y, Tong X. Deep octree-based CNNs with output-guided skip connections for 3D shape and scene completion, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020:1074-1081.
Yang J Y, Alv J M, Liu M M. Self-supervised learning of depth inference for multi-view stereo. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021:7522-7530.
Park J J, Florence P, Straub J, et al. DeepSDF: learning continuous signed distance functions for shape representation. 2019 Conference on Computer Vision and Pattern Recognition, 2019:165- 174.
Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60 (6):84-90.
LI Mingyang, Chen Wei, Wang Shanshan, et al. Review of 3D reconstruction methods for visual deep learning. Computer Science and Exploration, 2022, 1-26.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
