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.
Date: November 2017. Source: ACM Transactions on Graphics (TOG) – Proceedings of ACM SIGGRAPH Asia 2017. Abstract: Humans move their hands and bodies together to communicate and solve tasks. Capturing and replicating such coordinated activity is critical for virtual characters that behave realistically. Surprisingly, most methods treat the 3D modeling and tracking of bodies and…
Date: November 2017. Source: Machine Vision and Applications (2017). https://doi.org/10.1007/s00138-017-0887-6. Abstract: Registering a 3D facial model onto a 2D image is important for constructing pixel-wise correspondences between different facial images. The registration is based on a 3 ×× 4 dimensional projection matrix, which is obtained from pose estimation. Conventional pose estimation approaches employ facial landmarks…
Date: November 2017. Source: Head & Face Medicine 2017 13:19. Background: Orthognathic surgery is associated with considerable swelling and neurosensory disturbances. Serious swelling can lead to great physical and psychological strain. A randomized, prospective, controlled clinical trial was realized in order to evaluate the effect of a preoperative intravenous dexamethasone injection of 40 mg on…
Date: August 2017 Source: SIGGRAPH 2017, Los Angeles, CA, USA Overview: Researchers at the Max Planck Institute for Intelligent Systems (MPI-IS) have developed technology to digitally capture clothing on moving people, turn it into a 3D digital form, and dress virtual avatars with it. This new technology makes virtual clothing try-on practical. ClothCap uses 4D…
During his tour of Under Armour’s factory with CEO Kevin Plank, Sunday TODAY’s Willie Geist gets a 3D body model of himself created with the 3dMD technology the company uses to make custom clothes for athletes.
3dMD CEO Chris Lane presents the application of our temporal-3dMDbody (motion) systems to the next generation of wearable technology innovations at the Wear 2017 Conference in San Francisco, USA.
3dMD CEO Chris Lane presented the latest advances in temporal-3D (motion) camera systems for human subject input applications that demand anatomical image precision such as the next generation of face, gesture, and body movement recognition innovations @IEEEorg Automatic Face and Gesture Recognition Conference #FG2017.
3dMD is excited to be taking part in a fascinating experiment studying facial expressions in collaboration with researchers from Imperial College London as part of the Science Museum’s ongoing Live Science programme from 10 April 2017 – 2 July 2017 in London. During the experiment visitors are asked to make a range of facial expressions…
Date: March 2017. Source: researchgate.net (goo.gl/scholar/d1zUSr) Abstract: We address the problem of estimating human body shape from 3D scans over time. Reliable estimation of 3D body shape is necessary for many applications including virtual try-on, health monitoring, and avatar creation for virtual reality. Scanning bodies in minimal clothing, however, presents a practical barrier to these…