Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition
This work addresses the challenge of enhancing 3D face modeling and recognition for applications in computer vision, though it is incremental as it builds on existing 3D morphable models.
The paper tackles the problem of jointly performing 3D face reconstruction from single 2D images and face recognition by proposing an encoder-decoder network that disentangles shape features, resulting in improved accuracy in both tasks compared to existing methods.
This paper proposes an encoder-decoder network to disentangle shape features during 3D face reconstruction from single 2D images, such that the tasks of reconstructing accurate 3D face shapes and learning discriminative shape features for face recognition can be accomplished simultaneously. Unlike existing 3D face reconstruction methods, our proposed method directly regresses dense 3D face shapes from single 2D images, and tackles identity and residual (i.e., non-identity) components in 3D face shapes explicitly and separately based on a composite 3D face shape model with latent representations. We devise a training process for the proposed network with a joint loss measuring both face identification error and 3D face shape reconstruction error. To construct training data we develop a method for fitting 3D morphable model (3DMM) to multiple 2D images of a subject. Comprehensive experiments have been done on MICC, BU3DFE, LFW and YTF databases. The results show that our method expands the capacity of 3DMM for capturing discriminative shape features and facial detail, and thus outperforms existing methods both in 3D face reconstruction accuracy and in face recognition accuracy.