Data-driven 3D human head reconstruction

This paper proposes a framework for reconstructing 3D human head models from a single image. Firstly, a preprocessing system for images is designed. The image is automatically segmented using convolutional neural network. The Gabor filter is used to extract the direction of the hair, and a optional manual interaction is used to modify the results. Secondly, the parameters of the FLAME face parametric model are solved by using landmark points as constraint. The high-frequency information of the face image is used to enhance the detail, and the texture map is complemented by the albedo parameterized model. Finally, a strip mesh hair database is constructed, and the hair in the image is reconstructed by using this database and the information extracted from the image. (C) 2019 Elsevier Ltd. All rights reserved.