Latent Image Animator: Learning to Animate Images via Latent Space Navigation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Latent Image Animator: Learning to Animate Images via Latent Space Navigation

Résumé

Due to the remarkable progress of deep generative models, animating images has become increasingly efficient, whereas associated results have become increasingly realistic. Current animation-approaches commonly exploit structure representation extracted from driving videos. Such structure representation is instrumental in transferring motion from driving videos to still images. However, such approaches fail in case the source image and driving video encompass large appearance variation. Moreover, the extraction of structure information requires additional modules that endow the animation-model with increased complexity. Deviating from such models, we here introduce the Latent Image Animator (LIA), a self-supervised autoencoder that evades need for structure representation. LIA is streamlined to animate images by linear navigation in the latent space. Specifically, motion in generated video is constructed by linear displacement of codes in the latent space. Towards this, we learn a set of orthogonal motion directions simultaneously, and use their linear combination, in order to represent any displacement in the latent space. Extensive quantitative and qualitative analysis suggests that our model systematically and significantly outperforms state-of-art methods on VoxCeleb, Taichi and TED-talk datasets w.r.t. generated quality.
Fichier principal
Vignette du fichier
latent_image_animator_learning.pdf (15.82 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03714584 , version 1 (05-07-2022)

Identifiants

  • HAL Id : hal-03714584 , version 1

Citer

Yaohui Wang, Di Yang, Francois Bremond, Antitza Dantcheva. Latent Image Animator: Learning to Animate Images via Latent Space Navigation. ICLR 2022 - The International Conference on Learning Representations, Apr 2022, Virtual, France. ⟨hal-03714584⟩
71 Consultations
163 Téléchargements

Partager

Gmail Facebook X LinkedIn More