Face reconstruction is the task of recovering the facial geometry of a face from an image.
( Image credit: Microsoft Deep3DFaceReconstruction )
Our CNN works with just a single 2D facial image, does not require accurate alignment nor establishes dense correspondence between images, works for arbitrary facial poses and expressions, and can be used to reconstruct the whole 3D facial geometry (including the non-visible parts of the face) bypassing the construction (during training) and fitting (during testing) of a 3D Morphable Model.
#2 best model for 3D Face Reconstruction on Florence
We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment.
SOTA for Face Alignment on AFLW-LFPA
In this paper, we propose to tackle these three challenges in an new alignment framework termed 3D Dense Face Alignment (3DDFA), in which a dense 3D Morphable Model (3DMM) is fitted to the image via Cascaded Convolutional Neural Networks.
SOTA for Face Alignment on AFLW
The 3D shapes of faces are well known to be discriminative.
#4 best model for 3D Face Reconstruction on Florence (Average 3D Error metric)
Motivated by the concept of bump mapping, we propose a layered approach which decouples estimation of a global shape from its mid-level details (e. g., wrinkles).
Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency. However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce.
Over the last years, with the advent of Generative Adversarial Networks (GANs), many face analysis tasks have accomplished astounding performance, with applications including, but not limited to, face generation and 3D face reconstruction from a single "in-the-wild" image.
The network learns to generate faces from voices by matching the identities of generated faces to those of the speakers, on a training set.