HairShifter: Consistent and High-Fidelity Video Hair Transfer via Anchor-Guided Animation

TL;DR

HairShifter introduces a novel framework for high-fidelity, temporally consistent video hair transfer by combining image transfer techniques with animation, achieving state-of-the-art results in visual quality and coherence.

Contribution

The paper presents a new 'Anchor Frame + Animation' framework that unifies image hair transfer with smooth video animation, ensuring high quality and temporal consistency.

Findings

Achieves state-of-the-art performance in video hairstyle transfer.

Maintains hairstyle fidelity and temporal coherence across frames.

Demonstrates superior visual quality and scalability.

Abstract

Hair transfer is increasingly valuable across domains such as social media, gaming, advertising, and entertainment. While significant progress has been made in single-image hair transfer, video-based hair transfer remains challenging due to the need for temporal consistency, spatial fidelity, and dynamic adaptability. In this work, we propose HairShifter, a novel "Anchor Frame + Animation" framework that unifies high-quality image hair transfer with smooth and coherent video animation. At its core, HairShifter integrates a Image Hair Transfer (IHT) module for precise per-frame transformation and a Multi-Scale Gated SPADE Decoder to ensure seamless spatial blending and temporal coherence. Our method maintains hairstyle fidelity across frames while preserving non-hair regions. Extensive experiments demonstrate that HairShifter achieves state-of-the-art performance in video hairstyle transfer, combining superior visual quality, temporal consistency, and scalability. The code will be publicly available. We believe this work will open new avenues for video-based hairstyle transfer and establish a robust baseline in this field.