MegActor: Harness the Power of Raw Video for Vivid Portrait Animation

TL;DR

MegActor is a novel diffusion-based portrait animation method that effectively uses raw videos by addressing identity leakage and background interference through synthetic data, segmentation, and style transfer.

Contribution

Introduces MegActor, a pioneering conditional diffusion model that leverages raw videos for portrait animation by mitigating identity leakage and background issues.

Findings

Achieves results comparable to commercial models using only public datasets.

Effectively mitigates identity leakage with synthetic data generation.

Maintains background stability through CLIP-based encoding.

Abstract

Despite raw driving videos contain richer information on facial expressions than intermediate representations such as landmarks in the field of portrait animation, they are seldom the subject of research. This is due to two challenges inherent in portrait animation driven with raw videos: 1) significant identity leakage; 2) Irrelevant background and facial details such as wrinkles degrade performance. To harnesses the power of the raw videos for vivid portrait animation, we proposed a pioneering conditional diffusion model named as MegActor. First, we introduced a synthetic data generation framework for creating videos with consistent motion and expressions but inconsistent IDs to mitigate the issue of ID leakage. Second, we segmented the foreground and background of the reference image and employed CLIP to encode the background details. This encoded information is then integrated into the network via a text embedding module, thereby ensuring the stability of the background. Finally, we further style transfer the appearance of the reference image to the driving video to eliminate the influence of facial details in the driving videos. Our final model was trained solely on public datasets, achieving results comparable to commercial models. We hope this will help the open-source community.The code is available at https://github.com/megvii-research/MegFaceAnimate.