Enhanced Flexible Mold Lifetime for Roll‐to‐Roll Scaled‐Up Manufacturing of Adhesive Complex Microstructures
Bioinspired Microstructured Adhesives with Facile and Fast Switchability for Part Manipulation in Dry and Wet Conditions
Smart Materials for manipulation and actuation of small-scale structures
3D nanofabrication of various materials for advanced multifunctional microrobots
Liquid Crystal Mesophase of Supercooled Liquid Gallium And Eutectic Gallium–Indium
Machine Learning-Based Pull-off and Shear Optimal Adhesive Microstructures
Information entropy to detect order in self-organizing systems
Individual and collective manipulation of multifunctional bimodal droplets in three dimensions
Microrobot collectives with reconfigurable morphologies and functions
Self-organization in heterogeneous and non-reciprocal regime
Biomimetic Emulsion Systems
Giant Unilamellar Vesicles for Designing Cell-like Microrobots
Bioinspired self-assembled colloidal collectives drifting in three dimensions underwater
Accurate 3D Body Shape Regression using Metric and Semantic Attributes
] estimates metrically accurate body shape from an image by exploiting side information in the form of linguistic shape descriptions. While methods that regress 3D human meshes from images have progressed rapidly, the estimated body shapes often do not capture the true human shape. This is problematic since, for many applications, accurate body shape is as important as pose. The key reason that body shape accuracy lags pose accuracy is the lack of data. While humans can label 2D joints, and these constrain 3D pose, it is not so easy to “label” 3D body shape. Since paired data with images and 3D body shape are rare, we exploit two sources of partial information: (1) we collect internet images of diverse models together with a small set of measurements; (2) we collect semantic shape attributes for a wide range of 3D body meshes and model images. Taken together, these datasets provide sufficient constraints to infer metric 3D shape. We exploit this partial and semantic data in several novel ways to train a neural network, called SHAPY, that regresses 3D human pose and shape from an RGB image. We evaluate SHAPY on public benchmarks but note that they either lack significant body shape variation, ground-truth shape, or clothing variation. Thus, we collect a new dataset for 3D human shape estimation, containing photos of people in the wild for whom we have ground-truth 3D body scans. On this new benchmark, SHAPY significantly outperforms recent state-of-the-art methods on the task of 3D body shape estimation. This is the first demonstration that a 3D body shape regressor can be trained from sparse measurements and easy-to-obtain semantic shape attributes. Our model and data will be freely available for research.
Members
Publications