Single Source One Shot Reenactment using Weighted motion From Paired Feature Points

TL;DR

This paper introduces a novel face reenactment model that uses shape-independent motion features and paired feature points, enabling high-quality, identity-preserving animations from a single source image across multiple object types.

Contribution

It presents a new self-supervised approach that learns motion features independently of shape, generalizing to various objects with only one source image.

Findings

Faithfully transfers motion while preserving identity

Works for faces and non-face objects

Effective in cross-person reenactment scenarios

Abstract

Image reenactment is a task where the target object in the source image imitates the motion represented in the driving image. One of the most common reenactment tasks is face image animation. The major challenge in the current face reenactment approaches is to distinguish between facial motion and identity. For this reason, the previous models struggle to produce high-quality animations if the driving and source identities are different (cross-person reenactment). We propose a new (face) reenactment model that learns shape-independent motion features in a self-supervised setup. The motion is represented using a set of paired feature points extracted from the source and driving images simultaneously. The model is generalised to multiple reenactment tasks including faces and non-face objects using only a single source image. The extensive experiments show that the model faithfully transfers the driving motion to the source while retaining the source identity intact.