radames/PIFu-upright-standing

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

https://github.com/shunsukesaito/PIFu

This a checkpoint from the original project here are some important notes:

Warning: The released model is trained with mostly upright standing scans with weak perspectie projection and the pitch angle of 0 degree. Reconstruction quality may degrade for images highly deviated from trainining data.

@InProceedings{saito2019pifu,
author = {Saito, Shunsuke and Huang, Zeng and Natsume, Ryota and Morishima, Shigeo and Kanazawa, Angjoo and Li, Hao},
title = {PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}