MoFA: Model-Based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction
2017 IEEE International Conference on Computer Vision (ICCV)
Our model-based deep convolutional face autoencoder enables unsupervised learning of semantic pose, shape, expression, reflectance and lighting parameters. The trained encoder predicts these parameters from a single monocular image, all at once. Abstract In this work we propose a novel model-based deep convolutional autoencoder that addresses the highly challenging problem of reconstructing a 3D human face from a single in-the-wild color image. To this end, we combine a convolutional encoder
... work with an expert-designed generative model that serves as decoder. The core innovation is the differentiable parametric decoder that encapsulates image formation analytically based on a generative model. Our decoder takes as input a code vector with exactly defined semantic meaning that encodes detailed face pose, shape, expression, skin reflectance and scene illumination. Due to this new way of combining CNN-based with model-based face reconstruction, the CNN-based encoder learns to extract semantically meaningful parameters from a single monocular input image. For the first time, a CNN encoder and an expert-designed generative model can be trained end-to-end in an unsupervised manner, which renders training on very large (unlabeled) real world data feasible. The obtained reconstructions compare favorably to current state-of-the-art approaches in terms of quality and richness of representation.