TY  - JOUR
AU  - Gemma Rotger
AU  - Francesc Moreno-Noguer
AU  - Felipe Lumbreras
AU  - Antonio Agudo
PY  - 2019//
TI  - Detailed 3D face reconstruction from a single RGB image
KW  - 3D Wrinkle Reconstruction
KW  - Face Analysis
KW  - Optimization.
N2  - This paper introduces a method to obtain a detailed 3D reconstruction of facial skin from a single RGB image.To this end, we propose the exclusive use of an input image without requiring any information about the observed material nor training data to model the wrinkle properties. They are detected and characterized directly from the image via a simple and effective parametric model, determining several features such as location, orientation, width, and height. With these ingredients, we propose to minimize a photometric error to retrieve the final detailed 3D map, which is initialized by current techniques based on deep learning. In contrast with other approaches, we only require estimating a depth parameter, making our approach fast and intuitive. Extensive experimental evaluation is presented in a wide variety of synthetic and real images, including different skin properties and facialexpressions. In all cases, our method outperforms the current approaches regarding 3D reconstruction accuracy, providing striking results for both large and fine wrinkles.
UR  - http://wscg.zcu.cz/WSCG2019/!_2019_Journal_WSCG-2.pdf
N1  - ADAS; 600.086; 600.130; 600.122
ID  - Gemma Rotger2019
ER  -