EchoVideo: Identity-Preserving Human Video Generation by Multimodal Feature Fusion

TL;DR

EchoVideo introduces a novel multimodal feature fusion approach with a two-stage training strategy to improve identity preservation and reduce artifacts in human video generation.

Contribution

It proposes the EchoVideo framework with high-level semantic feature integration and a stochastic training method to enhance identity fidelity in video synthesis.

Findings

Effective identity preservation in generated videos

Reduced artifacts and improved visual quality

High controllability and fidelity in outputs

Abstract

Recent advancements in video generation have significantly impacted various downstream applications, particularly in identity-preserving video generation (IPT2V). However, existing methods struggle with "copy-paste" artifacts and low similarity issues, primarily due to their reliance on low-level facial image information. This dependence can result in rigid facial appearances and artifacts reflecting irrelevant details. To address these challenges, we propose EchoVideo, which employs two key strategies: (1) an Identity Image-Text Fusion Module (IITF) that integrates high-level semantic features from text, capturing clean facial identity representations while discarding occlusions, poses, and lighting variations to avoid the introduction of artifacts; (2) a two-stage training strategy, incorporating a stochastic method in the second phase to randomly utilize shallow facial information. The objective is to balance the enhancements in fidelity provided by shallow features while mitigating excessive reliance on them. This strategy encourages the model to utilize high-level features during training, ultimately fostering a more robust representation of facial identities. EchoVideo effectively preserves facial identities and maintains full-body integrity. Extensive experiments demonstrate that it achieves excellent results in generating high-quality, controllability and fidelity videos.