Dense Human Correspondences using Convolutional Networks

October 19, 2016
2:00 pm - 5:30 pm
Hall C

Track: General
Type: Posters
Level: All

We introduce a deep neural network structure for computing dense correspondences between shapes of clothed subjects in arbitrary poses. We demonstrate the effectiveness of this method by matching full or partial scans of people with arbitrary clothing and poses.


, 3D Graphics Researcher, Adobe Research