|Speaker || ||Gül Varol |
|Date || ||October 12th, 2018(Friday) |
|Time || ||14:30 |
|Location || ||Faculty of Computer and Informatics, Computer Lab. (4305) |
Human shape estimation is an important task for video editing, animation and fashion industry. Predicting 3D human bodyshape from natural images, however, is highly challenging due to factors such as variation in human bodies, clothing and viewpoint. We propose BodyNet, an end-to-end trainable neural network for direct inference of volumetric body shape from a single image. First, I will present our recently released SURREAL dataset that consists of synthetic images of people whose 3D annotations are automatically collected. Then, I will show the advantages of the BodyNet components: (i) a volumetric 3D loss, (ii) a multi-view re-projection loss, and (iii) intermediate supervision of 2D pose, 2D body part segmentation, and 3D pose. Our results and the dataset open up new possibilities for advancing person analysis using cheap and large-scale synthetic data.
More at: https://www.di.ens.fr/willow/research/bodynet/
Gül Varol is a PhD student in Inria and Ecole Normale Supérieure under the supervisions of Ivan Laptev and Cordelia Schmid. Her research is focused on human understanding in videos. Before joining Inria, she received bachelor and master degrees both in computer engineering from Bogazici University.