RAP: Real-time Audio-driven Portrait Animation with Video Diffusion Transformer
This addresses the need for efficient, high-quality portrait animation for applications like virtual avatars or video conferencing, representing a strong incremental advance by optimizing for real-time deployment.
The paper tackles the problem of generating realistic talking head videos from audio and a single image under real-time constraints, achieving state-of-the-art performance with precise audio control and high visual fidelity.
Audio-driven portrait animation aims to synthesize realistic and natural talking head videos from an input audio signal and a single reference image. While existing methods achieve high-quality results by leveraging high-dimensional intermediate representations and explicitly modeling motion dynamics, their computational complexity renders them unsuitable for real-time deployment. Real-time inference imposes stringent latency and memory constraints, often necessitating the use of highly compressed latent representations. However, operating in such compact spaces hinders the preservation of fine-grained spatiotemporal details, thereby complicating audio-visual synchronization RAP (Real-time Audio-driven Portrait animation), a unified framework for generating high-quality talking portraits under real-time constraints. Specifically, RAP introduces a hybrid attention mechanism for fine-grained audio control, and a static-dynamic training-inference paradigm that avoids explicit motion supervision. Through these techniques, RAP achieves precise audio-driven control, mitigates long-term temporal drift, and maintains high visual fidelity. Extensive experiments demonstrate that RAP achieves state-of-the-art performance while operating under real-time constraints.