Neural Puppet: Generative Layered Cartoon Characters

TL;DR

This paper introduces a learning-based method for generating new animations of cartoon characters from a few example images, using a layered 2.5D mesh model and differentiable rendering to handle diverse poses and artistic effects.

Contribution

It presents a novel architecture that predicts mesh deformations from sparse images, enabling high-quality animation synthesis without structured input data.

Findings

Outperforms state-of-the-art techniques in template fitting.

Successfully generates in-between frames and deformations.

Handles artistic variations like shading and motion effects.

Abstract

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.