Head2HeadFS: Video-based Head Reenactment with Few-shot Learning

TL;DR

Head2HeadFS introduces a fast, adaptable video-based head reenactment method that transfers head pose and expression using few-shot learning and dense 3D face information, improving quality and personalization.

Contribution

The paper presents a novel pipeline for head reenactment that combines dense 3D face shape conditioning with few-shot learning for rapid personalization.

Findings

High-quality expression and pose transfer achieved

Fast adaptation from generic to person-specific models

Effective use of dense 3D face information

Abstract

Over the past years, a substantial amount of work has been done on the problem of facial reenactment, with the solutions coming mainly from the graphics community. Head reenactment is an even more challenging task, which aims at transferring not only the facial expression, but also the entire head pose from a source person to a target. Current approaches either train person-specific systems, or use facial landmarks to model human heads, a representation that might transfer unwanted identity attributes from the source to the target. We propose head2headFS, a novel easily adaptable pipeline for head reenactment. We condition synthesis of the target person on dense 3D face shape information from the source, which enables high quality expression and pose transfer. Our video-based rendering network is fine-tuned under a few-shot learning strategy, using only a few samples. This allows for fast adaptation of a generic generator trained on a multiple-person dataset, into a person-specific one.