Deformations in Deep Models for Image and Video Generation

Seminar  by Stéphane Lathuilière, Télécom Paris

Friday, 18 October 2019, 14:30 – 15:30, room F107

INRIA Montbonnot Saint-Martin

 

Abstract: Generating realistic images and videos has countless applications in different areas, ranging from photography technologies to e-commerce business. Recently, deep generative approaches have emerged as effective techniques for generation tasks. In this talk, we will first present the problem of pose-guided person image generation. Specifically, given an image of a person and a target pose, a new image of that person in the target pose is synthesized. We will show that important body-pose changes affect generation quality and that specific feature map deformations lead to better images. Then, we will present our recent framework for video generation. More precisely, our approach generates videos where an object in a source image is animated according to the motion of a driving video. In this task, we employ a motion representation based on keypoints that are learned in a self-supervised fashion. Therefore, our approach can animate any arbitrary object without using annotation or prior information about the specific object to animate.

Biography: Stéphane Lathulière (PhD 2018, Université Grenoble Alpes, MSc 2014, ENSIMAG) is assistant professor at Télécom Paris since September 2019. Previous to that he was a post-doctoral fellow at Trento University (2018-2019) and a PhD candidate in the Perception team, at Inria Grenoble and at Université Grenoble Alpes (2014-2018).

Comments are closed.