VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior
This work improves audio-driven talking head generation for applications like virtual avatars and video synthesis, though it is incremental as it builds on existing methods.
The paper tackles the problem of generating high-quality talking head videos from audio by addressing the one-to-many mapping between audio and motion, resulting in a model that outperforms previous state-of-the-art works in objective and subjective comparisons with enhanced lip-sync and realism.
Audio-driven talking head generation has drawn much attention in recent years, and many efforts have been made in lip-sync, expressive facial expressions, natural head pose generation, and high video quality. However, no model has yet led or tied on all these metrics due to the one-to-many mapping between audio and motion. In this paper, we propose VividTalk, a two-stage generic framework that supports generating high-visual quality talking head videos with all the above properties. Specifically, in the first stage, we map the audio to mesh by learning two motions, including non-rigid expression motion and rigid head motion. For expression motion, both blendshape and vertex are adopted as the intermediate representation to maximize the representation ability of the model. For natural head motion, a novel learnable head pose codebook with a two-phase training mechanism is proposed. In the second stage, we proposed a dual branch motion-vae and a generator to transform the meshes into dense motion and synthesize high-quality video frame-by-frame. Extensive experiments show that the proposed VividTalk can generate high-visual quality talking head videos with lip-sync and realistic enhanced by a large margin, and outperforms previous state-of-the-art works in objective and subjective comparisons.