A Poisson equation-based method for 3D reconstruction of animated images. (English) Zbl 07452823

Summary: 3D reconstruction techniques for animated images and animation techniques for faces are important research in computer graphics-related fields. Traditional 3D reconstruction techniques for animated images mainly rely on expensive 3D scanning equipment and a lot of time-consuming postprocessing manually and require the scanned animated subject to remain in a fixed pose for a considerable period. In recent years, the development of large-scale computing power of computer-related hardware, especially distributed computing, has made it possible to come up with a real-time and efficient solution. In this paper, we propose a 3D reconstruction method for multivisual animated images based on Poisson’s equation theory. The calibration theory is used to calibrate the multivisual animated images, obtain the internal and external parameters of the camera calibration module, extract the feature points from the animated images of each viewpoint by using the corner point detection operator, then match and correct the extracted feature points by using the least square median method, and complete the 3D reconstruction of the multivisual animated images. The experimental results show that the proposed method can obtain the 3D reconstruction results of multivisual animation images quickly and accurately and has certain real-time and reliability.


68-XX Computer science
92-XX Biology and other natural sciences
Full Text: DOI


[1] Padcharoen, A.; Kitkuan, D.; Kumam, P.; Rilwan, J.; Kumam, W., Accelerated alternating minimization algorithm for Poisson noisy image recovery, Inverse Problems in Science and Engineering, 28, 7, 1031-1056 (2020) · Zbl 1465.94015
[2] Smallman, L.; Underwood, W.; Artemiou, A., Simple Poisson PCA: an algorithm for (sparse) feature extraction with simultaneous dimension determination, Computational Statistics, 35, 2, 559-577 (2020) · Zbl 1482.62020
[3] Shiba, S.; Sagara, H., Iterative reconstruction algorithm comparison using Poisson noise distributed sinogram data in passive gamma emission tomography, Journal of Nuclear Science and Technology, 58, 6, 659-666 (2021)
[4] Zhu, L.; Xing, X.; Zhu, Y.; Peng, W.; Yuan, Z.; Xia, Q., An advanced time-series InSAR approach based on Poisson curve for soft clay highway deformation monitoring, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 7682-7698 (2021)
[5] Chen, S.; Jin, M.; Zhang, Y.; Zhang, C., Infrared blind-pixel compensation algorithm based on generative adversarial networks and Poisson image blending, Signal, Image and Video Processing, 14, 1, 77-85 (2020)
[6] Gao, T.; He, X., Wavelet frame based denoising algorithm for color image with Poisson noise, Nanjing Xinxi Gongcheng Daxue Xuebao, 12, 5, 614-618 (2020) · Zbl 1474.42122
[7] Xu, T.; Demmer, R. T.; Li, G., Zero-inflated Poisson factor model with application to microbiome read counts, Biometrics, 77, 1, 91-101 (2021)
[8] Correia, S.; Guimarães, P.; Zylkin, T., Fast Poisson estimation with high-dimensional fixed effects, The Stata Journal, 20, 1, 95-115 (2020)
[9] Ahlmann-Eltze, C.; Huber, W., glmGamPoi: fitting Gamma-Poisson generalized linear models on single cell count data, Bioinformatics, 36, 24, 5701-5702 (2021)
[10] Lee, S. C. K., Addressing imbalanced insurance data through zero-inflated Poisson regression with boosting, ASTIN Bulletin: The Journal of the IAA, 51, 1, 27-55 (2021) · Zbl 1471.91466
[11] Caprace, D. G.; Gillis, T.; Chatelain, P., FLUPS: a Fourier-based library of unbounded Poisson solvers, SIAM Journal on Scientific Computing, 43, 1, C31-C60 (2021) · Zbl 1464.35063
[12] Li, J.; Yue, D. W., Modeling and analysis of distributed millimeter wave massive MIMO system using Poisson point processes, Wireless Networks, 26, 8, 6125-6138 (2020)
[13] Cui, Y.; Li, Q.; Zhu, F., Flexible bivariate Poisson integer-valued GARCH model, Annals of the Institute of Statistical Mathematics, 72, 6, 1449-1477 (2020) · Zbl 1467.62142
[14] Gao, M.; Zhao, J.; Sun, W., Stochastic H2/H∞ control for discrete-time mean-field systems with Poisson jump, Journal of the Franklin Institute, 358, 6, 2933-2947 (2021) · Zbl 1464.93084
[15] Tat, J.; Crawford, J.; Chong, J., Three-dimensional (3D) animation and calculation for the assessment of engaging Hill-Sachs lesions with computed tomography 3D reconstruction, Arthroscopy, sports medicine, and rehabilitation, 3, 1, e89-e96 (2021)
[16] Mickleburgh, H. L.; Nilsson Stutz, L.; Fokkens, H., Digital archaeology of death and burial. Using 3D reconstruction, visualization and simulation to frame past experience, Doing Digital Humanities, Concepts, Approaches, Cases, 121-145 (2020), Linnaeus University Press
[17] Li, Z.; Chen, L.; Liu, C.; Zhang, F.; Li, Z.; Gao, Y.; Ha, Y.; Xu, C.; Quan, S.; Xu, Y., Animated 3D human avatars from a single image with GAN-based texture inference, Computers & Graphics, 95, 81-91 (2021)
[18] Mickleburgh, H. L.; Stutz, L. N.; Fokkens, H., Virtual archaeology of death and burial: a procedure for integrating 3D visualization and analysis in archaeothanatology, Open Archaeology, 7, 1, 540-555 (2021)
[19] Mahayuddin, Z. R.; Saifuddin Saif, A. F. M., A comprehensive review towards segmentation and detection of cancer cell and tumor for dynamic 3D reconstruction, Asia-Pacific Journal of Information Technology and Multimedia, 9, 1, 28-39 (2020)
[20] Díaz, G. M.; Mohr-Bell, D.; Garrett, M.; Muñoz, L.; Lencinas, J. D., Customizing unmanned aircraft systems to reduce forest inventory costs: can oblique images substantially improve the 3D reconstruction of the canopy?, International Journal of Remote Sensing, 41, 9, 3480-3510 (2020)
[21] Cao, M.; Zheng, L.; Jia, W.; Lu, H.; Liu, X., Accurate 3-D reconstruction under IoT environments and its applications to augmented reality, IEEE Transactions on Industrial Informatics, 17, 3, 2090-2100 (2021)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.