Date: April 2019. Source: Cornell University Library – arXiv.org, Computer Vision and Pattern Recognition. Abstract: Large datasets are the cornerstone of recent advances in computer vision using deep learning. In contrast, existing human motion capture (mocap) datasets are small and the motions limited, hampering progress on learning models of human motion. While there are many…
Date: April 2019. Source: Cornell University Library – arXiv.org, Computer Vision and Pattern Recognition. Abstract: Generative Adversarial Networks (GANs) are currently the method of choice for generating visual data. Certain GAN architectures and training methods have demonstrated exceptional performance in generating realistic synthetic images (in particular, of human faces). However, for 3D object, GANs still…
Date: October 2018. Source: 9th 3DBODY.TECH Conference and Expo. October 16-17, 2018. Lugano, Switzerland, USA. Presenter: Chris LANE, 3dMD Ltd. Session: Technical Session 10: Full Body Scanning & Processing
Date: October 2018. Source: 9th 3DBODY.TECH Conference and Expo. October 16-17, 2018. Lugano, Switzerland, USA. Presenter: Mia K Markey Session: Technical Session 3: 3D Face & Body Scanning in Medicine Abstract: Autologous fat grafting is increasingly employed to address volume asymmetry and contour irregularity following breast reconstruction for breast cancer. However, there are no well-established…
Date: September 2018. Source: Sports Engineering, Volume 21, Issue 3, pp 217–225. Abstract: In snowboarding, the wrist is the most common injury site, as snowboarders often put their arms out to cushion a fall. This can result in a compressive load through the carpals coupled with wrist hyperextension, leading to ligament sprains or carpal and…
Date: September 2018. Source: 15th European Conference on Computer Vision (ECCV), Munich, Germany. Abstract: We present a novel method to generate accurate and realistic clothing deformation from real data capture. Previous methods for realistic cloth modeling mainly rely on intensive computation of physics-based simulation (with numerous heuristic parameters), while models reconstructed from visual observations typically…
Date: September 2018. Source: 15th European Conference on Computer Vision (ECCV), Munich, Germany, (pp 704-720). Abstract: Learned 3D representations of human faces are useful for computer vision problems such as 3D face tracking and reconstruction from images, as well as graphics applications such as character generation and animation. Traditional models learn a latent representation of…
Date: September 2018. Source: Computational Statistics & Data Analysis, Volume 125, pp 57-69. Highlights: • A novel scale space technique for analyzing spherical data is proposed. • Distributions of normal vector directions computed from a 3dMDhead image are analyzed. • A movie is a convenient way to explore the maps included in a SphereSiZer atlas.…
Date: July 2018. Source: International Conference on Applied Human Factors and Ergonomics (AHFE 2018). Advances in Human Factors in Simulation and Modeling. Advances in Intelligent Systems and Computing, Vol 780, pp 433-445. Springer. Abstract: This paper presents a registration framework for the construction of a statistical shape model of the human hand in a standard…
Date: July 2018. Source: Cornell University Library – arXiv.org, Computer Science, Computer Vision. Abstract: Objects that undergo non-rigid deformation are common in the real world. A typical and challenging example is the human faces. While various techniques have been developed for deformable shape registration and classification, benchmarks with detailed labels and landmarks suitable for evaluating…