Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision. S Sanyal, T Bolkart, H Feng, MJ Black.

Date: June 2019. Source: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA. Proceedings Page(s): 7755-7764. Abstract: 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. Robustness requires a large training set of in-the-wild…

Dense 3D Face Decoding Over 2500FPS: Joint Texture and Shape Convolutional Mesh Decoders. Y Zhou, Ji Deng, I Kotsia, S Zafeiriou.

Date: June 2019. Source: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA. Abstract: 3D Morphable Models (3DMMs) are statistical models that represent facial texture and shape variations using a set of linear bases and more particular Principal Component Analysis (PCA). 3DMMs were used as statistical priors for reconstructing 3D…

Smile dimensions in adult African American and Caucasian females and males. NM Souccar, DW Bowen, Z Syed, TA Swain, CH Kau, DM Sarver.

Date: May 2019. Source: Orthodontics & Craniofacial Research. https://doi.org/10.1111/ocr.12278. Objective: To test smile dimension variations in adult African American and Caucasian females and males. Setting and Sample Population: The University of Alabama at Birmingham School of Dentistry and Hospital. Three hundred and ninety‐four participants were recruited; African American females and males distributed over five age…

3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation. S Moschoglou, S Ploumpis, MA Nicolaou et al.

Date: May 2019. Source: International Journal of Computer Vision (2020). https://doi.org/10.1007/s11263-020-01329-8. Abstract: Over the past few years, Generative Adversarial Networks (GANs) have garnered increased interest among researchers in Computer Vision, with applications including, but not limited to, image generation, translation, imputation, and super-resolution. Nevertheless, no GAN-based method has been proposed in the literature that can…

EDAR, LYPLAL1, PRDM16, PAX3, DKK1, TNFSF12, CACNA2D3, and SUPT3H gene variants influence facial morphology in a Eurasian population. Y Li, W Zhao, D Li et al.

Date: April 2019. Source: Human Genetics 138, 681–689 (2019). https://doi.org/10.1007/s00439-019-02023-7. Abstract: In human society, the facial surface is visible and recognizable based on the facial shape variation which represents a set of highly polygenic and correlated complex traits. Understanding the genetic basis underlying facial shape traits has important implications in population genetics, developmental biology, and…

UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition. J Deng, S Cheng, N Xue, Y Zhou, S Zafeiriou.

UVDB is a dataset developed for training the proposed UV-GAN. It has been built from three different sources with the first subset containing 3,564 subjects (3,564 unique identities with six expressions, 21,384 unique UV maps in total) scanned by the 3dMD device.

Dyna: A Model of Dynamic Human Shape in Motion. G Pons-Moll, J Romero, N Mahmood, MJ Black.

Date: August 2015. Source: SIGGRAPH 2015. Journal ACM Transactions on Graphics (TOG), Volume 34 Issue 4, Article No. 120. SIGGRAPH Presentation: https://youtu.be/mWthea2K8-Q Abstract: To look human, digital full-body avatars need to have soft-tissue deformations like those of real people. We learn a model of soft-tissue deformations from examples using a high-resolution 4D capture system and…

Successfully Taking Hundreds of 3D Medical Photographs Daily. K Duncan.

Date: March 2012. Source: IMI News. Article: With a highly ambitious goal of building the world’s largest database of 3D facial images for vital research into face shape patterns, clinical teams from Great Ormond Street Hospital, University College Hospital, Eastman Dental Hospital and the Institute recently launched the “Me in 3D” initiative in the London…