| Citation: | XU G，JIN J C，TANG Z H，et al. Semantic part based single-view implicit field for 3D shape reconstruction technology[J]. Journal of Beijing University of Aeronautics and Astronautics，2025，51（3）：833-844 （in Chinese） doi: 10.13700/j.bh.1001-5965.2023.0089
|
With the development of deep learning techniques, learning implicit field for 3D shape reconstruction has become a heated topic, because implicit field can help networks learn a reasonable and sophisticated reconstruction model than explicit methods. However, there are still some challenges to be solved including lacking semantic information, local detail incompletions and so on. Thus, rather than recreating the entire model from a decoder directly, we first reconstruct the semantic components of a single model using an implicit filed structure based on semantic sections in our paper. Then we aggregate the reconstructed semantic parts together to get the final model. Finally, we test those results on the public 3D shape dataset PartNet and compare them to other cutting-edge single-view reconstruction approaches. It’s obvious that using a semantic part-based implicit field can learn more reasonable shape representations for reconstruction.
| [1] |
LI M Y, ZHANG H. D2IM-Net: Learning detail disentangled implicit fields from single images[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2021: 10241-10250.
|
| [2] |
PARK J J, FLORENCE P, STRAUB J, et al. DeepSDF: learning continuous signed distance functions for shape representation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2019: 165-174.
|
| [3] |
HORN B K P. Shape from shading: a method for obtaining the shape of a smooth opaque object from one view[M]. America: Project on Mathematics and Computation, 1970: 4-5.
|
| [4] |
包晓敏, 白晨. 单目三维重建技术综述[J]. 智能计算机与应用, 2020, 10(7): 49-52. doi: 10.3969/j.issn.2095-2163.2020.07.011
BAO X M, BAI C. Overview of monocular 3D reconstruction techniques[J]. Intelligent Computer and Applications, 2020, 10(7): 49-52(in Chinese). doi: 10.3969/j.issn.2095-2163.2020.07.011
|
| [5] |
GENG J. Structured-light 3D surface imaging: a tutorial[J]. Advances in Optics and Photonics, 2011, 3(2): 128-160. doi: 10.1364/AOP.3.000128
|
| [6] |
陈荣, 许宏丽, 杨东学, 等. 一种基于空间编码结构光的稠密三维重建算法[J]. 西安电子科技大学学报, 2021, 48(6): 123-130.
CHEN R, XU H L, YANG D X, et al. A dense 3D reconstruction algorithm based on spatially encoded structured light[J]. Journal of Xidian University, 2021, 48(6): 123-130(in Chinese).
|
| [7] |
SNAVELY N, SEITZ S M, SZELISKI R. Photo tourism: exploring photo collections in 3D[J]. ACM Transactions on Graphics, 2006, 25(3): 835-846. doi: 10.1145/1141911.1141964
|
| [8] |
LOWE D G. Object recognition from local scale-invariant features[C]//Proceedings of the Seventh IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 2002: 1150-1157.
|
| [9] |
CHOY C B, XU D F, GWAK J, et al. 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction[M]//Lecture Notes in Computer Science. Berlin: Springer International Publishing, 2016: 628-644.
|
| [10] |
SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. (2015-04-10)[2023-01-01]. https://arxiv.org/abs/1409.1556.
|
| [11] |
WU J, ZHANG C, XUE T, et al. Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling[C]//Proceedings of the 30th International Conference on Neural Information Processing Systems. New York: MIT Press, 2016: 82-90.
|
| [12] |
XIE H Z, YAO H X, SUN X S, et al. Pix2Vox: context-aware 3D reconstruction from single and multi-view images[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE Press, 2019: 2690-2698.
|
| [13] |
WU J, WANG Y, XUE T, et al. Marrnet: 3D shape reconstruction via 2.5 d sketches[C]//Proceedings of the International Conference on Neural Information Processing Systems. New York: MIT Press, 2017: 171-190.
|
| [14] |
WANG H Q, YANG J L, LIANG W, et al. Deep single-view 3D object reconstruction with visual hull embedding[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 8941-8948. doi: 10.1609/aaai.v33i01.33018941
|
| [15] |
PONTES J K, KONG C, SRIDHARAN S, et al. Image2Mesh: a learning framework for single image 3D reconstruction[M]//Lecture Notes in Computer Science. Berlin: Springer International Publishing, 2019: 365-381.
|
| [16] |
JACK D, PONTES J K, SRIDHARAN S, et al. Learning free-form deformations for 3D object reconstruction[M]//Lecture Notes in Computer Science. Berlin: Springer International Publishing, 2019: 317-333.
|
| [17] |
LI K J, PHAM T, ZHAN H Y, et al. Efficient dense point cloud object reconstruction using deformation vector fields[M]//Lecture Notes in Computer Science. Berlin: Springer International Publishing, 2018: 508-524.
|
| [18] |
KONG C, LIN C H, LUCEY S. Using locally corresponding CAD models for dense 3D reconstructions from a single image[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 5603-5611.
|
| [19] |
GROUEIX T, FISHER M, KIM V G, et al. A papier-Mache approach to learning 3D surface generation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2018: 216-224.
|
| [20] |
CHEN Z Q, ZHANG H. Learning implicit fields for generative shape modeling[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2019: 5932-5941.
|
| [21] |
MESCHEDER L, OECHSLE M, NIEMEYER M, et al. Occupancy networks: learning 3D reconstruction in function space[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2019: 4455-4465.
|
| [22] |
WANG T C, LIU M Y, ZHU J Y, et al. High-resolution image synthesis and semantic manipulation with conditional GANs[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2018: 8798-8807.
|
| [23] |
BECHTOLD J, TATARCHENKO M, FISCHER V, et al. Fostering generalization in single-view 3D reconstruction by learning a hierarchy of local and global shape priors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2021: 15875-15884.
|
| [24] |
MO K C, ZHU S L, CHANG A X, et al. PartNet: a large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2019: 909-918.
|
| [1] | LIU X W，XU X Y，HUANG H，et al. Analysis of power reflux problem and its solution of THS[J]. Journal of Beijing University of Aeronautics and Astronautics，2025，51（3）：874-880 （in Chinese）. doi: 10.13700/j.bh.1001-5965.2023.0110. |
| [2] | HUANG Zhijie, LIU Wei, GUO Zhiqiang. Optimization Design of LLC Resonant Converters for Efficiency and Power Density Based on Genetic Algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2024.0891 |
| [3] | SHAO Z Z，ZHENG K，DONG S，et al. Design of double bending rotary ultrasonic elliptical vibration machining system[J]. Journal of Beijing University of Aeronautics and Astronautics，2024，50（9）：2912-2918 （in Chinese）. doi: 10.13700/j.bh.1001-5965.2022.0712. |
| [4] | HAN F Q，ZHANG D Y. Ultrasonic longitudinal torsional and low frequency torsional compound vibration tapping experiment[J]. Journal of Beijing University of Aeronautics and Astronautics，2024，50（4）：1077-1084 （in Chinese）. doi: 10.13700/j.bh.1001-5965.2022.0453. |
| [5] | ZHAO Jin-peng, CENG Wei, MA Hai-teng. Method for determining Stanton number on the blunt body in supersonic flow[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0800 |
| [6] | HU D W，LI S S，LIU G H. Research progress on influence of disturbance of abiotic environmental factors on microbial community succession[J]. Journal of Beijing University of Aeronautics and Astronautics，2024，50（9）：2677-2687 （in Chinese）. doi: 10.13700/j.bh.1001-5965.2022.0736. |
| [7] | WANG Bo, HE Yang, DU Xiao-xin, ZHANG Jian-fei, XU Jing-ran, JIA Na. Prediction of Microbe-drug association based on graph attention stacked autoencoder[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0730 |
| [8] | HE Xing-yue, YANG Jing, ZHU Zhao-qiang, YANG Bin, TAN Tao. VMD-HPCA-GRU ultra-short-term wind power forecasting based on COOT algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0255 |
| [9] | HAN M T，XU Z C，CHANG Q，et al. Soil moisture retrieval using Beidou GEO satellite interference signal power[J]. Journal of Beijing University of Aeronautics and Astronautics，2023，49（7）：1661-1670 （in Chinese）. doi: 10.13700/j.bh.1001-5965.2021.0478. |
| [10] | RUAN H L，HONG X B，WANG Y N，et al. Power measurement deviations of direct and reflected signals from BDS GEO satellites in ground-based GNSS-R applications[J]. Journal of Beijing University of Aeronautics and Astronautics，2023，49（4）：825-831 （in Chinese）. doi: 10.13700/j.bh.1001-5965.2022.0080. |
| [11] | ZHOU Z G，WANG J，LI Y，et al. Ultrasonic array testing and evaluation method of multilayer bonded structures[J]. Journal of Beijing University of Aeronautics and Astronautics，2023，49（12）：3207-3214 （in Chinese）. doi: 10.13700/j.bh.1001-5965.2022.0084. |
| [12] | DONG Jie, SU Yu-lin, ZHANG Da-cheng. Multi-level degradation-based prognostics for micro direct methanol fuel cells[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0517 |
| [13] | NIU G C，WANG Y Y，TIAN Y B. LiDAR obstacle detection based on improved density clustering[J]. Journal of Beijing University of Aeronautics and Astronautics，2023，49（10）：2608-2616 （in Chinese）. doi: 10.13700/j.bh.1001-5965.2021.0733. |
| [14] | ZHOU Yu, XIA Hao, LIU Hong-yu, BAI Lei. DPC clustering algorithm based on K-reciprocal Neighbors and kernel density estimation[J]. Journal of Beijing University of Aeronautics and Astronautics. doi: 10.13700/j.bh.1001-5965.2023.0342 |
| [15] | ZHANG X W，ZHANG M，YU D Y，et al. Analysis of influence of ultrasonic drilling structure parameters on output characteristics[J]. Journal of Beijing University of Aeronautics and Astronautics，2023，49（7）：1735-1742 （in Chinese）. doi: 10.13700/j.bh.1001-5965.2021.0554. |
| [16] | LI Wenxuan, JIAO Wenhai, WANG Kai, QIU Ruijin, SUN Shuxian. Monitoring and analysis on GPS P(Y) code power enhancement[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(11): 2193-2203. doi: 10.13700/j.bh.1001-5965.2021.0676 |
| [17] | LI Yongping, ZHU Guangwu, ZHENG Xiaoliang, AI Jiangzhao, YAN Yafei, ZHOU Jianhua. In-situ measurement of atmospheric density in very low Earth orbits[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(10): 1875-1882. doi: 10.13700/j.bh.1001-5965.2021.0618 |
| [18] | YANG Jialin, LIN Chunyu, NIE Lang, LIU Meiqin, ZHAO Yao. Crowd density estimation for fisheye images[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(8): 1455-1463. doi: 10.13700/j.bh.1001-5965.2021.0520 |
| [19] | ZHANG Zhiwen, DU Wenjie, LIANG Junfei, ZHANG Yangang, WU Yawen. Layered control of hybrid power loader based on fuel cell[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(11): 2165-2176. doi: 10.13700/j.bh.1001-5965.2021.0099 |
| [20] | XIANG Yan, LI Wen, GUO Zhibin, ZHANG Jin, LU Shanfu. Research progress on key materials of phosphoric acid doped high-temperature proton exchange membrane fuel cells[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(9): 1791-1805. doi: 10.13700/j.bh.1001-5965.2022.0575 |
Figures(9) / Tables(4)
Copyright © Journal of Beijing University of Aeronautics and Astronautics
Address: Editorial Department of Journal of Beijing University of Aeronautics and Astronautics, 37 Xueyuan Road, Haidian District, Beijing Post Code: 100191 Email: jbuaa@buaa.edu.cn
Supported by:
Beijing Renhe Information Technology Co., Ltd.
Xue Xiaochun, Yang Bin. Calculation Research of the Radar Cross Section[J]. Journal of Beijing University of Aeronautics and Astronautics, 1998, 24(5): 549-551. (in Chinese)
DownLoad:
