Image Animation with Perturbed Masks

TL;DR

This paper introduces a novel image animation method that animates objects without pose models, using perturbed masks and a shared mask generator, trained solely on reconstructing frames from the same video.

Contribution

The method animates arbitrary objects without prior pose models and only during test-time, outperforming state-of-the-art techniques on multiple benchmarks.

Findings

Outperforms existing methods on multiple benchmarks

Does not require pose models or prior structural knowledge

Works with arbitrary objects during test-time

Abstract

We present a novel approach for image-animation of a source image by a driving video, both depicting the same type of object. We do not assume the existence of pose models and our method is able to animate arbitrary objects without the knowledge of the object's structure. Furthermore, both, the driving video and the source image are only seen during test-time. Our method is based on a shared mask generator, which separates the foreground object from its background, and captures the object's general pose and shape. To control the source of the identity of the output frame, we employ perturbations to interrupt the unwanted identity information on the driver's mask. A mask-refinement module then replaces the identity of the driver with the identity of the source. Conditioned on the source image, the transformed mask is then decoded by a multi-scale generator that renders a realistic image, in which the content of the source frame is animated by the pose in the driving video. Due to the lack of fully supervised data, we train on the task of reconstructing frames from the same video the source image is taken from. Our method is shown to greatly outperform the state-of-the-art methods on multiple benchmarks. Our code and samples are available at https://github.com/itsyoavshalev/Image-Animation-with-Perturbed-Masks.