2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2019
DOI: 10.1109/cvpr.2019.01107
|View full text |Cite
|
Sign up to set email alerts
|

FML: Face Model Learning From Videos

Abstract: Figure 1. We propose multi-frame self-supervised training of a deep network based on in-the-wild video data for jointly learning a face model and 3D face reconstruction. Our approach successfully disentangles facial shape, appearance, expression, and scene illumination. AbstractMonocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on d… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
162
1

Year Published

2019
2019
2020
2020

Publication Types

Select...
5
2
1

Relationship

2
6

Authors

Journals

citations
Cited by 172 publications
(163 citation statements)
references
References 71 publications
0
162
1
Order By: Relevance
“…. Several other works have shown that combining a prior template about the object category shape with video allows for an improved 3D reconstruction of the underlying geometry, both for faces [67,63,43] and quadrupeds [8]. However, these methods still require multiple videos and a template, while our method does not.…”
Section: Previous Workmentioning
confidence: 92%
See 1 more Smart Citation
“…. Several other works have shown that combining a prior template about the object category shape with video allows for an improved 3D reconstruction of the underlying geometry, both for faces [67,63,43] and quadrupeds [8]. However, these methods still require multiple videos and a template, while our method does not.…”
Section: Previous Workmentioning
confidence: 92%
“…Effectively all works addressing aspects related to 3D geometry rely on paired data for training, e.g. multiple views of the same object [71], videos [48] or some pre-existing 3D mesh representation that is the starting point for further disentanglement [21,56,81,62] or self-supervision [85].…”
Section: Previous Workmentioning
confidence: 99%
“…Recently, several deep learning-based models were published that fall into this group of nonlinear models [Bagautdinov et al 2018;Lombardi et al 2018;Tewari et al 2019Tran and Liu 2018a]. Section 6 covers these models in more detail.…”
Section: Multiplicative Modelsmentioning
confidence: 99%
“…The rise of deep learning methods facilitated to learn per-vertex appearance models directly from images, such as done by , who learn per-vertex albedo model offsets in order to improve the generalization ability of an existing PCA-based model. Similarly, Tewari et al [2019], learn a per-vertex albedo model from scratch based on video data. train a mesh decoder that jointly models the texture and shape on a per-vertex basis, which, however, relies on the availability of 3D shape and appearance data.…”
Section: Nonlinear Modelsmentioning
confidence: 99%
“…Hence, in this work, we learn from complete texture maps obtained from 3D registrations. 3D person reconstruction from images While promising, recent methods for 3D person reconstruction either require video as input [6,7,8], scans [74], do not allow control over pose, shape and clothing [48,56], focus only on faces [72,32,63,57,47,62], or only on garments [68].…”
Section: Related Workmentioning
confidence: 99%