FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916956760702976 |
|---|---|
| author | Ki, Taekyung Min, Dongchan Chae, Gyeongsu |
| author_facet | Ki, Taekyung Min, Dongchan Chae, Gyeongsu |
| contents | With the rapid advancement of diffusion-based generative models, portrait image animation has achieved remarkable results. However, it still faces challenges in temporally consistent video generation and fast sampling due to its iterative sampling nature. This paper presents FLOAT, an audio-driven talking portrait video generation method based on flow matching generative model. Instead of a pixel-based latent space, we take advantage of a learned orthogonal motion latent space, enabling efficient generation and editing of temporally consistent motion. To achieve this, we introduce a transformer-based vector field predictor with an effective frame-wise conditioning mechanism. Additionally, our method supports speech-driven emotion enhancement, enabling a natural incorporation of expressive motions. Extensive experiments demonstrate that our method outperforms state-of-the-art audio-driven talking portrait methods in terms of visual quality, motion fidelity, and efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_01064 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait Ki, Taekyung Min, Dongchan Chae, Gyeongsu Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia Image and Video Processing With the rapid advancement of diffusion-based generative models, portrait image animation has achieved remarkable results. However, it still faces challenges in temporally consistent video generation and fast sampling due to its iterative sampling nature. This paper presents FLOAT, an audio-driven talking portrait video generation method based on flow matching generative model. Instead of a pixel-based latent space, we take advantage of a learned orthogonal motion latent space, enabling efficient generation and editing of temporally consistent motion. To achieve this, we introduce a transformer-based vector field predictor with an effective frame-wise conditioning mechanism. Additionally, our method supports speech-driven emotion enhancement, enabling a natural incorporation of expressive motions. Extensive experiments demonstrate that our method outperforms state-of-the-art audio-driven talking portrait methods in terms of visual quality, motion fidelity, and efficiency. |
| title | FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Multimedia Image and Video Processing |
| url | https://arxiv.org/abs/2412.01064 |