Real-time 3D face fitting and texture fusion on in-the-wild videos
- We present a fully automatic approach to real-time 3D face reconstruction from monocular in-the-wild videos. With the use of a cascaded-regressor-based face tracking and a 3D morphable face model shape fitting, we obtain a semidense 3D face shape. We further use the texture information from multiple frames to build a holistic 3D face representation from the video footage. Our system is able to capture facial expressions and does not require any person specific training. We demonstrate the robustness of our approach on the challenging 300 Videos in the Wild (300- VW) dataset. Our real-time fitting framework is available as an open-source library at http://4dface.org.
| Author of HS Reutlingen | Kopp, Philipp; Rätsch, Matthias |
|---|---|
| DOI: | https://doi.org/10.1109/LSP.2016.2643284 |
| ISSN: | 1070-9908 |
| Erschienen in: | IEEE signal processing letters : a publication of the IEEE Signal Processing Society |
| Publisher: | IEEE |
| Place of publication: | New York, NY |
| Document Type: | Journal article |
| Language: | English |
| Publication year: | 2017 |
| Tag: | 3D face reconstruction; 3D morphable face model; face model fitting; open source software; real-time |
| Volume: | 24 |
| Issue: | 4 |
| Page Number: | 5 |
| First Page: | 437 |
| Last Page: | 441 |
| DDC classes: | 620 Ingenieurwissenschaften und Maschinenbau |
| Open access?: | Nein |
| Licence (German): |  In Copyright - Urheberrechtlich geschützt |
