DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild

Güler, Rıza Alp; Trigeorgis, George; Antonakos, Epameinondas; Snape, Patrick; Zafeiriou, Stefanos; Kokkinos, Iasonas

doi:10.1109/cvpr.2017.280

Cited by 159 publications

(80 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these methods heavily rely on the high accuracy of landmarks or other feature points detector. Thus, some methods [28,29] firstly use CNNs to learn the dense correspondence between input image and 3D template, then calculate the 3DMM parameters with predicted dense constrains. Recent works also explore the usage of CNN to predict 3DMM parameters directly.…”

Section: D Face Reconstructionmentioning

confidence: 99%

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Feng

Shao

et al. 2018

Lecture Notes in Computer Science

649

583

View full text Add to dashboard Cite

We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment. To achieve this, we design a 2D representation called UV position map which records the 3D shape of a complete face in UV space, then train a simple Convolutional Neural Network to regress it from a single 2D image. We also integrate a weight mask into the loss function during training to improve the performance of the network. Our method does not rely on any prior face model, and can reconstruct full facial geometry along with semantic meaning. Meanwhile, our network is very light-weighted and spends only 9.8ms to process an image, which is extremely faster than previous works. Experiments on multiple challenging datasets show that our method surpasses other state-of-the-art methods on both reconstruction and alignment tasks by a large margin. Code is available at https://github.com/YadiraF/PRNet.

show abstract

Section: D Face Reconstructionmentioning

confidence: 99%

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Feng

Shao

et al. 2018

Lecture Notes in Computer Science

649

583

View full text Add to dashboard Cite

show abstract

“…In addition to optimization-based reconstruction approaches, there are many learning-based methods [72,41,27,20,56]. Among them there are methods that learn to detect fiducial points in images with high accuracy, e.g., based on CNNs [58,70,15] or Restricted Boltzmann Machines [67].…”

Section: Learning-based Approachesmentioning

confidence: 99%

Self-Supervised Multi-level Face Model Learning for Monocular Reconstruction at Over 250 Hz

Tewari

Zollhöfer

Garrido

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

289

266

View full text Add to dashboard Cite

Our novel monocular reconstruction approach estimates high-quality facial geometry, skin reflectance (including facial hair) and incident illumination at over 250 Hz. A trainable multi-level face representation is learned jointly with the feed forward inverse rendering network. End-to-end training is based on a self-supervised loss that requires no dense ground truth. AbstractThe reconstruction of dense 3D models of face geometry and appearance from a single image is highly challenging and ill-posed. To constrain the problem, many approaches rely on strong priors, such as parametric face models learned from limited 3D scan data. However, prior models restrict generalization of the true diversity in facial geometry, skin reflectance and illumination. To alleviate this problem, we present the first approach that jointly learns 1) a regressor for face shape, expression, reflectance and illumination on the basis of 2) a concurrently learned parametric face model. Our multi-level face model combines the advantage of 3D Morphable Models for regularization with the out-of-space generalization of a learned corrective space. We train end-to-end on in-the-wild images without dense annotations by fusing a convolutional encoder with a differentiable expert-designed renderer and a self-supervised training loss, both defined at multiple detail levels. Our approach compares favorably to the stateof-the-art in terms of reconstruction quality, better generalizes to real world faces, and runs at over 250 Hz.

show abstract

“…Richardson et al [21] improve the initial 3DMM estimate with the help of a fine-scale network that allows to recover mid-scale facial detail. CNNs have also been used for shape regression of 3D faces in-the-wild [13].…”

Section: Related Workmentioning

confidence: 99%

Multilinear Autoencoder for 3D Face Model Learning

Abrevaya

Wuhrer

Boyer

2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Generative models have proved to be useful tools to represent 3D human faces and their statistical variations. With the increase of 3D scan databases available for training, a growing challenge lies in the ability to learn generative face models that effectively encode shape variations with respect to desired attributes, such as identity and expression, given datasets that can be diverse. This paper addresses this challenge by proposing a framework that learns a generative 3D face model using an autoencoder architecture, allowing hence for weakly supervised training. The main contribution is to combine a convolutional neural network-based encoder with a multilinear model-based decoder, taking therefore advantage of both the convolutional network robustness to corrupted and incomplete data, and of the multilinear model capacity to effectively model and decouple shape variations. Given a set of 3D face scans with annotation labels for the desired attributes, e.g. identities and expressions, our method learns an expressive multilinear model that decouples shape changes due to the different factors. Experimental results demonstrate that the proposed method outperforms recent approaches when learning multilinear face models from incomplete training data, particularly in terms of space decoupling, and that it is capable of learning from an order of magnitude more data than previous methods.

show abstract

DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild

Cited by 159 publications

References 80 publications

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Self-Supervised Multi-level Face Model Learning for Monocular Reconstruction at Over 250 Hz

Multilinear Autoencoder for 3D Face Model Learning

Contact Info

Product

Resources

About