Abstract
In this report, we present our solution for track1, multi-view based 3D human body reconstruction, of the ECCV 2022 WCPA Challenge: From Face, Body and Fashion to 3D Virtual Avatars 1. We developed a variant network based on TetraTSDF to reconstruct detailed 3D human body models with canonical T-pose from that multi-view images of the same person with different actions and angles, which is called TetraTSDF++ in this report. This method first fuses the features of different views, then infers the volumetric truncated signed distance function (TSDF) in the preset human body shell, and finally obtains the human surface through marching cube algorithm. The best chamfer distance score of our solution is 0.9751, and our solution got the 2nd place on the leaderboard.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Authors, P.: PaddleSeg, end-to-end image segmentation kit based on paddlepaddle (2019). https://github.com/PaddlePaddle/PaddleSeg
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1251–1258 (2017)
Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4501–4510 (2019)
Liu, Y., et al.: PaddleSeg: a high-efficient development toolkit for image segmentation (2021)
Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graphics 34(6), 1–16 (2015)
Onizuka, H., Hayirci, Z., Thomas, D., Sugimoto, A., Uchiyama, H., Taniguchi, R.i.: Tetratsdf: 3D human reconstruction from a single image with a tetrahedral outer shell. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6011–6020 (2020)
Zheng, Z., Yu, T., Liu, Y., Dai, Q.: Pamir: Parametric model-conditioned implicit representation for image-based human reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3170–3184 (2021)
Zhu, X., et al.: MVP-human dataset for 3d human avatar reconstruction from unconstrained frames. arXiv preprint arXiv:2204.11184 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, X. (2023). Multi-view Canonical Pose 3D Human Body Reconstruction Based on Volumetric TSDF. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13805. Springer, Cham. https://doi.org/10.1007/978-3-031-25072-9_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-25072-9_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25071-2
Online ISBN: 978-3-031-25072-9
eBook Packages: Computer ScienceComputer Science (R0)