Thin-Plate Spline Motion Model for Image Animation

TL;DR

This paper introduces an unsupervised image animation framework using thin-plate spline motion estimation and multi-resolution occlusion masks, significantly improving motion transfer quality across diverse objects and large pose variations.

Contribution

The paper presents a novel end-to-end unsupervised motion transfer method employing thin-plate spline estimation and occlusion-aware feature fusion for enhanced image animation.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Effectively handles large pose gaps between source and driving images.

Produces high-quality animations for faces, bodies, and pixel art.

Abstract

Image animation brings life to the static object in the source image according to the driving video. Recent works attempt to perform motion transfer on arbitrary objects through unsupervised methods without using a priori knowledge. However, it remains a significant challenge for current unsupervised methods when there is a large pose gap between the objects in the source and driving images. In this paper, a new end-to-end unsupervised motion transfer framework is proposed to overcome such issue. Firstly, we propose thin-plate spline motion estimation to produce a more flexible optical flow, which warps the feature maps of the source image to the feature domain of the driving image. Secondly, in order to restore the missing regions more realistically, we leverage multi-resolution occlusion masks to achieve more effective feature fusion. Finally, additional auxiliary loss functions are designed to ensure that there is a clear division of labor in the network modules, encouraging the network to generate high-quality images. Our method can animate a variety of objects, including talking faces, human bodies, and pixel animations. Experiments demonstrate that our method performs better on most benchmarks than the state of the art with visible improvements in pose-related metrics.