On 3D Face Reconstruction via Cascaded Regression in Shape Space
It addresses incremental improvements in 3D face reconstruction for computer vision applications, focusing on practical integration and understanding of existing methods.
This paper investigates cascaded regression for 3D face reconstruction from single 2D images, analyzing factors like landmark and vertex counts, and proposes a simplified method that integrates with automated landmark detection to reconstruct faces with original pose and expression, achieving state-of-the-art performance in evaluations.
Cascaded regression has been recently applied to reconstructing 3D faces from single 2D images directly in shape space, and achieved state-of-the-art performance. This paper investigates thoroughly such cascaded regression based 3D face reconstruction approaches from four perspectives that are not well studied yet: (i) The impact of the number of 2D landmarks; (ii) the impact of the number of 3D vertices; (iii) the way of using standalone automated landmark detection methods; and (iv) the convergence property. To answer these questions, a simplified cascaded regression based 3D face reconstruction method is devised, which can be integrated with standalone automated landmark detection methods and reconstruct 3D face shapes that have the same pose and expression as the input face images, rather than normalized pose and expression. Moreover, an effective training method is proposed by disturbing the automatically detected landmarks. Comprehensive evaluation experiments have been done with comparison to other 3D face reconstruction methods. The results not only deepen the understanding of cascaded regression based 3D face reconstruction approaches, but also prove the effectiveness of proposed method.