Back to the Future: Joint Aware Temporal Deep Learning 3D Human Pose Estimation

1 code implementation • 22 Feb 2020 • 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 estimation.

3D Human Pose Estimation Action Detection +1

Uncalibrated Deflectometry with a Mobile Device on Extended Specular Surfaces

no code implementations • 24 Jul 2019 • Florian Willomitzer, Chia-Kai Yeh, Vikas Gupta, William Spies, Florian Schiffers, Marc Walton, Oliver Cossairt

We introduce a system and methods for the three-dimensional measurement of extended specular surfaces with high surface normal variations.

Automatic Trimap Generation for Image Matting

no code implementations • 2 Jul 2017 • Vikas Gupta, Shanmuganathan Raman

We use learning based matting method to generate the matte from the automatically generated trimap.

Image Matting