3D Face Reconstruction
76 papers with code • 7 benchmarks • 11 datasets
3D Face Reconstruction is a computer vision task that involves creating a 3D model of a human face from a 2D image or a set of images. The goal of 3D face reconstruction is to reconstruct a digital 3D representation of a person's face, which can be used for various applications such as animation, virtual reality, and biometric identification.
( Image credit: 3DDFA_V2 )
Libraries
Use these libraries to find 3D Face Reconstruction models and implementationsDatasets
Most implemented papers
Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
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.
Dense Face Alignment
Face alignment is a classic problem in the computer vision field.
Extreme 3D Face Reconstruction: Seeing Through Occlusions
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).
ExpNet: Landmark-Free, Deep, 3D Facial Expressions
Our ExpNet CNN is applied directly to the intensities of a face image and regresses a 29D vector of 3D expression coefficients.
3D Face From X: Learning Face Shape from Diverse Sources
Although 3D scanned data contain accurate geometric information of face shapes, the capture system is expensive and such datasets usually contain a small number of subjects.
MobileFace: 3D Face Reconstruction with Efficient CNN Regression
Estimation of facial shapes plays a central role for face transfer and animation.
3D Face Modeling From Diverse Raw Scan Data
Traditional 3D face models learn a latent representation of faces using linear subspaces from limited scans of a single database.
GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction
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.
Dual Attention MobDenseNet(DAMDNet) for Robust 3D Face Alignment
3D face alignment of monocular images is a crucial process in the recognition of faces with disguise. 3D face reconstruction facilitated by alignment can restore the face structure which is helpful in detcting disguise interference. This paper proposes a dual attention mechanism and an efficient end-to-end 3D face alignment framework. We build a stable network model through Depthwise Separable Convolution, Densely Connected Convolutional and Lightweight Channel Attention Mechanism.
DF2Net: A Dense-Fine-Finer Network for Detailed 3D Face Reconstruction
In addition, we introduce three types of data to train these networks, including 3D model synthetic data, 2D image reconstructed data, and fine facial images.