We present a method for training a regression network from image pixels to 3D morphable model coordinates using only unlabeled photographs. The training loss is based on features from a facial recognition network, computed onthe-fly by rendering the predicted faces with a differentiable renderer. To make training from features feasible and avoid network fooling effects, we introduce three objectives: a batch distribution loss that encourages the output distribution to match the distribution of the morphable model, a loopback loss that ensures the network can correctly reinterpret its own output, and a multi-view identity loss that compares the features of the predicted 3D face and the input photograph from multiple viewing angles. We train a regression network using these objectives, a set of unlabeled photographs, and the morphable model itself, and demonstrate state-of-the-art results. nition network [25] into identity parameters for the Basel 2017 Morphable Face Model [8].to-image autoencoder with a fixed, morphable-model-based decoder and an image-based loss [28]. This paper presents a method for training a regression network that removes both the need for supervised training data and the reliance on inverse rendering to reproduce image pixels. Instead, the network learns to minimize a loss based on the facial identity features produced by a face recognition network such as VGG-Face [17] or Google's FaceNet [25]. These features are robust to pose, expression, lighting, and even non-photorealistic inputs. We exploit this 1 arXiv:1806.06098v1 [cs.CV]

No abstract

No abstract