Reconstruction of a Three-Dimensional Human Model from a Single Image

Main Article Content

Alexander Sergeevich Tarasov
Vlada Vladimirovna Kugurakova

Abstract

This article focuses on improving the 3D reconstruction of a human model from a single pixel-aligned implicit function image presented by FaceBook Research. The drawbacks of the method are revealed, associated with limiting the quality of the original image, recommendations are presented to avoid its incorrect operation, and approaches to improve the original model are proposed, which increase the identity of the resulting model by 1.33 times. We also worked out the tactics of subsequent texture mapping and implementation of a set of animations.

Article Details

References

1. Lassner, C. et al. Unite the people: Closing the loop between 3d and 2d human representations [Текст] / C. Lassner, J. Romero, M. Kiefel, F. Bogo, M. J. Black, P. V. Gehler // Proceedings of the IEEE conference on computer vision and pattern recognition. – 2017. – P. 6050-6059.
2. Sun, Z. 3D printing in medicine: current applications and future directions [Текст] / Z. Sun / Quantitative imaging in medicine and surgery. – 2018. – V. 8. – №. 11. – P. 1069.
3. Демоверсия редактора создания персонажа / Официальный сайт the Sims 4: [Электронный ресурс]. – https://www.ea.com/ru-ru/games/the-sims/the-sims-4/pc/create-a-sim-demo (дата обращения: 29.03.2021).
4. Weng, C. Y., Curless, B. Photo wake-up: 3d character animation from a single photo [Текст] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. – 2019. – P. 5908-5917.
5. Alldieck, T. et al. Tex2shape: Detailed full human body geometry from a single image [Текст] / T. Alldieck, G. Pons-Moll, C. Theobalt, M. Magnor // Proceedings of the IEEE/CVF International Conference on Computer Vision. – 2019. – P. 2293-2303.
6. Saito, S. et al. Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization [Текст] / S. Saito, Z. Huang, R. Natsume, S. Morishima, A. Kanazawa, H. Li // Proceedings of the IEEE/CVF International Conference on Computer Vision. – 2019. – P. 2304-2314.
7. Chen, Y., Medioni , G. Object modelling by registration of multiple range images [Текст] // Image and vision computing. – 1992. – V. 10. – №. 3. – P. 145-155.
8. Pavlakos, G.et al. Learning to estimate 3D human pose and shape from a single color image [Текст] / G. Pavlakos, L. Zhu, X. Zhou // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. – 2018. – P. 459-468.
9. Saito, S. Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization [Текст] / S. Saito, T. Simon, J. Saragih, H. Joo // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. – 2020. – P. 84-93.
10. Giving people the power to build community through research and innovation / FaceBook Research [Электронный ресурс]. – URL: https://research.fb.com/
11. Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose / GitHub [Электронный ресурс]. – URL: https://github.com/Daniil-Osokin/lightweight-human-pose-estimation.pytorch
12. pix2pixHD / GitHub [Электронный ресурс]. – URL: https://github.com/NVIDIA/pix2pixHD
13. Blender 2.92 Reference Manual / Blender Documentation [Электронный ресурс]. – URL: https://docs.blender.org/manual/en/latest
14. MetaHuman Creator / Unreal Engine [Электронный ресурс]. – URL: https://www.unrealengine.com/en-US/metahuman-creator
15. The world’s most open and advanced real-time 3D creation tool / Unreal Engine [Электронный ресурс]. – URL: https://www.unrealengine.com/en-US/
16. Manage 3D content and export with one click / Quixel Bridge [Электронный ресурс]. – URL: https://quixel.com/bridge
17. Blind Face Restoration via Deep Multi-scale Component Dictionaries / GitHub [Электронный ресурс]. – URL: https://github.com/csxmli2016/DFDNet
18. Background Removal API / remove.bg [Электронный ресурс]. – URL: https://www.remove.bg/api
19. Animate 3D characters for games, film, and more. / Mixamo [Электронный ресурс]. – URL: https://www.mixamo.com
20. Тарасов А.С. Быстрое прототипирование трехмерного виртуального аватара и его движений на основе сканирования [Текст] / Выпускная квалификационная работа бакалавра Института информационных технологий и интеллектуальных систем // Казанский федеральный университет. – 2021. – 55 с.


Most read articles by the same author(s)

1 2 > >>