Tex2Shape: Detailed Full Human Body Geometry From a Single Image

Thiemo Alldieck, Gerard Pons-Moll, Christian Theobalt, Marcus Magnor; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 2293-2303

Abstract


We present a simple yet effective method to infer detailed full human body shape from only a single photograph. Our model can infer full-body shape including face, hair, and clothing including wrinkles at interactive frame-rates. Results feature details even on parts that are occluded in the input image. Our main idea is to turn shape regression into an aligned image-to-image translation problem. The input to our method is a partial texture map of the visible region obtained from off-the-shelf methods. From a partial texture, we estimate detailed normal and vector displacement maps, which can be applied to a low-resolution smooth body model to add detail and clothing. Despite being trained purely with synthetic data, our model generalizes well to real-world photographs. Numerous results demonstrate the versatility and robustness of our method.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Alldieck_2019_ICCV,
author = {Alldieck, Thiemo and Pons-Moll, Gerard and Theobalt, Christian and Magnor, Marcus},
title = {Tex2Shape: Detailed Full Human Body Geometry From a Single Image},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}