3D face reconstruction is the task of reconstructing a face from an image into a 3D form (or mesh).
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment.
SOTA for Face Alignment on AFLW-LFPA
The 3D shapes of faces are well known to be discriminative.
#3 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).
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.
SOTA for 3D Face Reconstruction on Florence (Average 3D Error metric )
3D face reconstruction from a single 2D image is a challenging problem with broad applications.
SOTA for Face Alignment on AFLW2000-3D
In this paper, we take a radically different approach and harness the power of Generative Adversarial Networks (GANs) and DCNNs in order to reconstruct the facial texture and shape from single images.
The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions.
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.
With the powerfulness of convolution neural networks (CNN), CNN based face reconstruction has recently shown promising performance in reconstructing detailed face shape from 2D face images.