Paper Presentation

Date:

Deep Network for the Integrated 3D Sensing of Multiple People in Natural Images & Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound

Deep Network for the Integrated 3D Sensing of Multiple People in Natural Images

Automatic, feed-forward model, to predict the 3d body shape and pose of multiple people, given a single input image.

Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound

An unsupervised image-to-image translation framework, maximizing domain-specific variational information bound, learning the target domain-invariant representation of the two domains.

More information here