EasyGenNet: An Efficient Framework for Audio-Driven Gesture Video Generation Based on Diffusion Model
This addresses the problem of inefficient and data-intensive gesture-to-video systems for researchers and practitioners in multimedia generation, though it is incremental as it builds upon existing pre-trained models.
The paper tackles the challenge of synthesizing natural expressions and gestures in audio-driven cospeech video generation by proposing a simple one-stage training method and a temporal inference method based on a diffusion model, resulting in outperforming existing GAN-based and diffusion-based methods.
Audio-driven cospeech video generation typically involves two stages: speech-to-gesture and gesture-to-video. While significant advances have been made in speech-to-gesture generation, synthesizing natural expressions and gestures remains challenging in gesture-to-video systems. In order to improve the generation effect, previous works adopted complex input and training strategies and required a large amount of data sets for pre-training, which brought inconvenience to practical applications. We propose a simple one-stage training method and a temporal inference method based on a diffusion model to synthesize realistic and continuous gesture videos without the need for additional training of temporal modules.The entire model makes use of existing pre-trained weights, and only a few thousand frames of data are needed for each character at a time to complete fine-tuning. Built upon the video generator, we introduce a new audio-to-video pipeline to synthesize co-speech videos, using 2D human skeleton as the intermediate motion representation. Our experiments show that our method outperforms existing GAN-based and diffusion-based methods.