TY - CPAPER U1 - Konferenzveröffentlichung A1 - Huber, Patrik A1 - Feng, Zhen-Hua A1 - Christmas, William A1 - Kittler, Josef A1 - Rätsch, Matthias T1 - Fitting 3D morphable face models using local features T2 - 2015 IEEE International Conference on Image Processing (ICIP) : 27 - 30 Sept. 2015, Québec City, Canada N2 - In this paper, we propose a novel fitting method that uses local image features to fit a 3D morphable face model to 2D images. To overcome the obstacle of optimising a cost function that contains a non-differentiable feature extraction operator, we use a learning-based cascaded regression method that learns the gradient direction from data. The method allows to simultaneously solve for shape and pose parameters. Our method is thoroughly evaluated on morphable model generated data and first results on real data are presented. Compared to traditional fitting methods, which use simple raw features like pixel colour or edge maps, local features have been shown to be much more robust against variations in imaging conditions. Our approach is unique in that we are the first to use local features to fit a 3D morphable model. Because of the speed of our method, it is applicable for realtime applications. Our cascaded regression framework is available as an open source library at github.com/patrikhuber/ superviseddescent. KW - 3D morphable model KW - cascaded regression KW - 3D reconstruction KW - supervised descent Y1 - 2015 SN - 978-1-4799-8339-1 SB - 978-1-4799-8339-1 U6 - https://doi.org/10.1109/ICIP.2015.7350989 DO - https://doi.org/10.1109/ICIP.2015.7350989 SP - 1195 EP - 1199 S1 - 5 PB - IEEE CY - Piscataway, NJ ER -