First Order Motion Model for Image Animation - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

First Order Motion Model for Image Animation

Résumé

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. Our source code is publicly available.

Dates et versions

hal-04347801 , version 1 (15-12-2023)

Identifiants

Citer

Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci, Nicu Sebe. First Order Motion Model for Image Animation. Advances in Neural Information Processing Systems 32 (NeurIPS), Dec 2019, Vancouver (Canada), Canada. ⟨hal-04347801⟩
10 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More