Graph Convolutional Network with Probabilistic Spatial Regression: Application to Craniofacial Landmark Detection from 3D Photogrammetry. C Elkhill, S LeBeau, B French, AR Porras.
This excerpt will show up on the home page Blog/News feed
3D Photography to Quantify the Severity of Metopic Craniosynostosis. MK Bruce, WH Tao, J Beiriger, C Christensen, MJ Pfaff, R Whitaker, JA Goldstein.
Results of this study show that 3dMD photography is a valid alternative to CT for evaluation of head shape in MCS. Its use will provide an objective, quantifiable means of assessing outcomes in a rigorous manner while decreasing radiation exposure in this patient population.
Identity-Disentangled Neural Deformation Model for Dynamic Meshes. B Xu, L Ma, Y Ye, T Schmidt, CD Twigg, S Lovegrove.
Meta Reality Labs and Imperial College London build a neural hand deformation model with 3dMD’s real-world 3DH scan data, 2021.
Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation. M Bahri, E O’ Sullivan, S Gong, F Liu, X Liu, MM Bronstein, S Zafeiriou.
Imperial College London builds Shape My Face (2020), a 3D face registration model, with 3dMD’s real-world training and test data.
BLSM: A Bone-Level Skinned Model of the Human Mesh. H Wang, RA Guler, I Kokkinos, G Papandreou, S Zafeiriou.
Imperial College London builds BLSM (2020), a bone-level body mesh model, with 3dMD’s real-world training and evaluation data, presented at ECCV 2020.
Learning to Dress 3D People in Generative Clothing (CAPE). Q Ma, J Yang, A Ranjan, S Pujades, G Pons-Moll, S Tang, MJ Black.
MPI-IS trains its 2020 CAPE generative model for dressing 3D people in clothing with 3dMD’s 4D real-world body data.
Learning Multi-human Optical Flow. A Ranjan, DT Hoffmann, D Tzionas et al.
Date: January 2020. Source: International Journal of Computer Vision 128, 873–890 (2020). https://doi.org/10.1007/s11263-019-01279-w. Abstract: The optical flow of humans is well known to be useful for the analysis of human action. Recent optical flow methods focus on training deep networks to approach the problem. However, the training data used by them does not cover the…
Digital Twin: Acquiring High-Fidelity 3D Avatar from a Single Image. R Wang, CF Chen, H Peng, X Liu, O Liu, X Li.
Date: December 2019. Source: Cornell University Library – arXiv.org, Computer Vision and Pattern Recognition. Abstract: We present an approach to generate high fidelity 3D face avatar with a high-resolution UV texture map from a single image. To estimate the face geometry, we use a deep neural network to directly predict vertex coordinates of the 3D…
The Menpo Benchmark for Multi-pose 2D and 3D Facial Landmark Localisation and Tracking. J Deng, A Roussos, G Chrysos et al.
Date: November 2019. Source: International Journal of Computer Vision, Volume 127, pages 599–624, https://doi.org/10.1007/s11263-018-1134-y. Abstract: In this article, we present the Menpo 2D and Menpo 3D benchmarks, two new datasets for multi-pose 2D and 3D facial landmark localisation and tracking. In contrast to the previous benchmarks such as 300W and 300VW, the proposed benchmarks contain…
Synthesizing Facial Photometries and Corresponding Geometries Using Generative Adversarial Networks. G Shamai, R Slossberg, R Kimmel.
Date: October 2019. Source: ACM Transactions on Multimedia Computing, Communications, and Applications, Article No.: 87 https://doi.org/10.1145/3337067. Abstract: Artificial data synthesis is currently a well-studied topic with useful applications in data science, computer vision, graphics, and many other fields. Generating realistic data is especially challenging, since human perception is highly sensitive to non-realistic appearance. In recent…