Discriminative 3D morphable model fitting

This paper presents a novel discriminative method for estimating 3D shape from a single image with 3D Morphable Model (3DMM). Until now, most traditional 3DMM fitting methods depend on the analysis-by-synthesis framework which searches for the best parameters by minimizing the difference between the input image and the model appearance. They are highly sensitive to initialization and have to rely on the stochastic optimization to handle local minimum problem, which is usually a time-consuming process. To solve the problem, we find a different direction to estimate the shape parameters through learning a regressor instead of minimizing the appearance difference. Compared with the traditional analysis-by-synthesis framework, the new discriminative approach makes it possible to utilize large databases to train a robust fitting model which can reconstruct shape from image features accurately and efficiently. We compare our method with two popular 3DMM fitting algorithms on FRGC database. Experimental results show that our approach significantly outperforms the state-of-the-art in terms of efficiency, robustness and accuracy.