TY - GEN

T1 - Neural Puppet

T2 - 2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020

AU - Poursaeed, Omid

AU - Kim, Vladimir G.

AU - Shechtman, Eli

AU - Saito, Jun

AU - Belongie, Serge

N1 - Publisher Copyright: © 2020 IEEE.

PY - 2020/3

Y1 - 2020/3

N2 - We propose a learning based method for generating new animations of a cartoon character given a few example images. Our method is designed to learn from a traditionally animated sequence, where each frame is drawn by an artist, and thus the input images lack any common structure, correspondences, or labels. We express pose changes as a deformation of a layered 2.5D template mesh, and devise a novel architecture that learns to predict mesh deformations matching the template to a target image. This enables us to extract a common low-dimensional structure from a diverse set of character poses. We combine recent advances in differentiable rendering as well as mesh-aware models to successfully align common template even if only a few character images are available during training. In addition to coarse poses, character appearance also varies due to shading, out-of-plane motions, and artistic effects. We capture these subtle changes by applying an image translation network to refine the mesh rendering, providing an end-to-end model to generate new animations of a character with high visual quality. We demonstrate that our generative model can be used to synthesize in-between frames and to create data-driven deformation. Our template fitting procedure outperforms state-of-the-art generic techniques for detecting image correspondences.

AB - We propose a learning based method for generating new animations of a cartoon character given a few example images. Our method is designed to learn from a traditionally animated sequence, where each frame is drawn by an artist, and thus the input images lack any common structure, correspondences, or labels. We express pose changes as a deformation of a layered 2.5D template mesh, and devise a novel architecture that learns to predict mesh deformations matching the template to a target image. This enables us to extract a common low-dimensional structure from a diverse set of character poses. We combine recent advances in differentiable rendering as well as mesh-aware models to successfully align common template even if only a few character images are available during training. In addition to coarse poses, character appearance also varies due to shading, out-of-plane motions, and artistic effects. We capture these subtle changes by applying an image translation network to refine the mesh rendering, providing an end-to-end model to generate new animations of a character with high visual quality. We demonstrate that our generative model can be used to synthesize in-between frames and to create data-driven deformation. Our template fitting procedure outperforms state-of-the-art generic techniques for detecting image correspondences.

UR - http://www.scopus.com/inward/record.url?scp=85085497976&partnerID=8YFLogxK

U2 - 10.1109/WACV45572.2020.9093346

DO - 10.1109/WACV45572.2020.9093346

M3 - Conference article

AN - SCOPUS:85085497976

SP - 3335

EP - 3345

JO - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

JF - Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Y2 - 1 March 2020 through 5 March 2020

ER -