Název:	Detailed 3D Face Reconstruction from a Single RGB Image
Autoři:	Rotger, Gemma Moreno-Noguer, Francesc Lumbreras, Felipe Agudo, Antonio
Citace zdrojového dokumentu:	Journal of WSCG. 2019, vol. 27, no. 2, p. 103-112.
Datum vydání:	2019
Nakladatel:	Václav Skala - UNION Agency
Typ dokumentu:	článek article
URI:	http://hdl.handle.net/11025/35594
ISSN:	1213-6964 (on-line) 1213-6972 (print) 1213-6980 (CD-ROM)
Klíčová slova:	3D rekonstrukce vrásek;analýza obličeje;optimalizace
Klíčová slova v dalším jazyce:	3D wrinkle reconstruction;face analysis;optimization
Abstrakt v dalším jazyce:	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 facial expressions. In all cases, our method outperforms the current approaches regarding 3D reconstruction accuracy, providing striking results for both large and fine wrinkles.
Práva:	© Václav Skala - UNION Agency
Vyskytuje se v kolekcích:	Volume 27, Number 2 (2019)

Všechny záznamy v DSpace jsou chráněny autorskými právy, všechna práva vyhrazena.