3D Morphable Face Models—Past, Present, and Future

By B. Egger, W. Smith, Ayush Kumar Tewari, Stefanie Wuhrer, Michael Zollhöfer, Thabo Beeler, Florian Bernard, Timo Bolkart, A. Kortylewski, Sami Romdhani and 3 more. 2019

530 citations recorded by the source corpus.

In this article, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. The challenges in building and applying these models, namely, capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these areas. We also look ahead, identifying unsolved challenges, proposing directions for future research, and highlighting the broad range of current and future applications.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, 3D Vision & Pose

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

In 3D Vision & Pose

Citations in the corpus

GAN Inversion: A Survey (2021, methodology): “morphable model (3DMM) [178] with the input of Style-”
Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video (2020, background): “Most existing approaches thus limit themselves to a single object category, such as the human body [23, 87, 31] or face [12].”
StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images (2020, background): “For an in-depth overview of parametric face models and their possible applications we refer to the recent survey papers [10, 39].”
HeadNeRF: A Realtime NeRF-based Parametric Head Model (2021, methodology): “Early works of the parametric face/head model [3, 6, 11, 30, 41, 57] mainly model 3D faces with the topologically uniformed face template mesh and usually ignore to represent the non-face parts, such as hair and teeth.”
HexPlane: A Fast Representation for Dynamic Scenes (2023, background): “Similarly, category-speciﬁc priors like 3DMM [12] or SMPL [40] are even more powerful than deformation ﬁelds, which enormously improve results but are hardly limited to particular scenes.”
Advances, challenges and opportunities in creating data for trustworthy AI (2022, background): “Synthetic data can also exacerbate data disparity when digitally disadvantaged groups are not considered in simulator design 39,40 .”
EMOCA: Emotion Driven Monocular Face Capture and Animation (2022, background): “Monocular face reconstruction: Reconstructing 3D face shape from images has been studied extensively for more than two decades [22, 99].”