Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929356932120576 |
|---|---|
| author | Yang, Shiqi Zhong, Zhi Zhao, Mengjie Takahashi, Shusuke Ishii, Masato Shibuya, Takashi Mitsufuji, Yuki |
| author_facet | Yang, Shiqi Zhong, Zhi Zhao, Mengjie Takahashi, Shusuke Ishii, Masato Shibuya, Takashi Mitsufuji, Yuki |
| contents | In recent years, with the realistic generation results and a wide range of personalized applications, diffusion-based generative models gain huge attention in both visual and audio generation areas. Compared to the considerable advancements of text2image or text2audio generation, research in audio2visual or visual2audio generation has been relatively slow. The recent audio-visual generation methods usually resort to huge large language model or composable diffusion models. Instead of designing another giant model for audio-visual generation, in this paper we take a step back showing a simple and lightweight generative transformer, which is not fully investigated in multi-modal generation, can achieve excellent results on image2audio generation. The transformer operates in the discrete audio and visual Vector-Quantized GAN space, and is trained in the mask denoising manner. After training, the classifier-free guidance could be deployed off-the-shelf achieving better performance, without any extra training or modification. Since the transformer model is modality symmetrical, it could also be directly deployed for audio2image generation and co-generation. In the experiments, we show that our simple method surpasses recent image2audio generation methods. Generated audio samples can be found at https://docs.google.com/presentation/d/1ZtC0SeblKkut4XJcRaDsSTuCRIXB3ypxmSi7HTY3IyQ/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_14598 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation Yang, Shiqi Zhong, Zhi Zhao, Mengjie Takahashi, Shusuke Ishii, Masato Shibuya, Takashi Mitsufuji, Yuki Computer Vision and Pattern Recognition Machine Learning Multimedia Sound Audio and Speech Processing In recent years, with the realistic generation results and a wide range of personalized applications, diffusion-based generative models gain huge attention in both visual and audio generation areas. Compared to the considerable advancements of text2image or text2audio generation, research in audio2visual or visual2audio generation has been relatively slow. The recent audio-visual generation methods usually resort to huge large language model or composable diffusion models. Instead of designing another giant model for audio-visual generation, in this paper we take a step back showing a simple and lightweight generative transformer, which is not fully investigated in multi-modal generation, can achieve excellent results on image2audio generation. The transformer operates in the discrete audio and visual Vector-Quantized GAN space, and is trained in the mask denoising manner. After training, the classifier-free guidance could be deployed off-the-shelf achieving better performance, without any extra training or modification. Since the transformer model is modality symmetrical, it could also be directly deployed for audio2image generation and co-generation. In the experiments, we show that our simple method surpasses recent image2audio generation methods. Generated audio samples can be found at https://docs.google.com/presentation/d/1ZtC0SeblKkut4XJcRaDsSTuCRIXB3ypxmSi7HTY3IyQ/ |
| title | Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation |
| topic | Computer Vision and Pattern Recognition Machine Learning Multimedia Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2405.14598 |