2 papers
cs.CV2020
Back to the Future: Joint Aware Temporal Deep Learning 3D Human Pose Estimation
Vikas Gupta
We propose a new deep learning network that introduces a deeper CNN channel filter and constraints as losses to reduce joint position and motion errors for 3D video human body pose…
cs.CV2019
Uncalibrated Deflectometry with a Mobile Device on Extended Specular Surfaces
Florian Willomitzer, Chia-Kai Yeh, Vikas Gupta +4
We introduce a system and methods for the three-dimensional measurement of extended specular surfaces with high surface normal variations. Our system consists only of a mobile hand…