Timezone: »
Image animation consists of generating a video sequence so that an object in a source image is animated according to the motion of a driving video. Our framework addresses this problem without using any annotation or prior information about the specific object to animate. Once trained on a set of videos depicting objects of the same category (e.g. faces, human bodies), our method can be applied to any object of this class. To achieve this, we decouple appearance and motion information using a self-supervised formulation. To support complex motions, we use a representation consisting of a set of learned keypoints along with their local affine transformations. A generator network models occlusions arising during target motions and combines the appearance extracted from the source image and the motion derived from the driving video. Our framework scores best on diverse benchmarks and on a variety of object categories.
Author Information
Aliaksandr Siarohin (University of Trento)
Stéphane Lathuilière (Telecom-Paris)
Sergey Tulyakov (Snap Inc)
Elisa Ricci (FBK - Technologies of Vision)
Nicu Sebe (University of Trento)
More from the Same Authors
-
2021 Poster: Efficient Training of Visual Transformers with Small Datasets »
Yahui Liu · Enver Sangineto · Wei Bi · Nicu Sebe · Bruno Lepri · Marco Nadai -
2020 Poster: Latent World Models For Intrinsically Motivated Exploration »
Aleksandr Ermolov · Nicu Sebe -
2020 Spotlight: Latent World Models For Intrinsically Motivated Exploration »
Aleksandr Ermolov · Nicu Sebe -
2017 Poster: Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction »
Dan Xu · Wanli Ouyang · Xavier Alameda-Pineda · Elisa Ricci · Xiaogang Wang · Nicu Sebe