FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second

David Smith, Matthew Loper, Xiaochen Hu, Paris Mavroidis, Javier Romero; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 5330-5339

Abstract


Current methods for body shape estimation either lack detail or require many images. They are usually architecturally complex and computationally expensive. We propose FACSIMILE (FAX), a method that estimates a detailed body from a single photo, lowering the bar for creating virtual representations of humans. Our approach is easy to implement and fast to execute, making it easily deployable. FAX uses an image-translation network which recovers geometry at the original resolution of the image. Counterintuitively, the main loss which drives FAX is on per-pixel surface normals instead of per-pixel depth, making it possible to estimate detailed body geometry without any depth supervision. We evaluate our approach both qualitatively and quantitatively, and compare with a state-of-the-art method.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Smith_2019_ICCV,
author = {Smith, David and Loper, Matthew and Hu, Xiaochen and Mavroidis, Paris and Romero, Javier},
title = {FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}