Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913245741187072 |
|---|---|
| author | Xing, Yazhou He, Yingqing Tian, Zeyue Wang, Xintao Chen, Qifeng |
| author_facet | Xing, Yazhou He, Yingqing Tian, Zeyue Wang, Xintao Chen, Qifeng |
| contents | Video and audio content creation serves as the core technique for the movie industry and professional users. Recently, existing diffusion-based methods tackle video and audio generation separately, which hinders the technique transfer from academia to industry. In this work, we aim at filling the gap, with a carefully designed optimization-based framework for cross-visual-audio and joint-visual-audio generation. We observe the powerful generation ability of off-the-shelf video or audio generation models. Thus, instead of training the giant models from scratch, we propose to bridge the existing strong models with a shared latent representation space. Specifically, we propose a multimodality latent aligner with the pre-trained ImageBind model. Our latent aligner shares a similar core as the classifier guidance that guides the diffusion denoising process during inference time. Through carefully designed optimization strategy and loss functions, we show the superior performance of our method on joint video-audio generation, visual-steered audio generation, and audio-steered visual generation tasks. The project website can be found at https://yzxing87.github.io/Seeing-and-Hearing/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17723 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners Xing, Yazhou He, Yingqing Tian, Zeyue Wang, Xintao Chen, Qifeng Computer Vision and Pattern Recognition Multimedia Sound Audio and Speech Processing Video and audio content creation serves as the core technique for the movie industry and professional users. Recently, existing diffusion-based methods tackle video and audio generation separately, which hinders the technique transfer from academia to industry. In this work, we aim at filling the gap, with a carefully designed optimization-based framework for cross-visual-audio and joint-visual-audio generation. We observe the powerful generation ability of off-the-shelf video or audio generation models. Thus, instead of training the giant models from scratch, we propose to bridge the existing strong models with a shared latent representation space. Specifically, we propose a multimodality latent aligner with the pre-trained ImageBind model. Our latent aligner shares a similar core as the classifier guidance that guides the diffusion denoising process during inference time. Through carefully designed optimization strategy and loss functions, we show the superior performance of our method on joint video-audio generation, visual-steered audio generation, and audio-steered visual generation tasks. The project website can be found at https://yzxing87.github.io/Seeing-and-Hearing/ |
| title | Seeing and Hearing: Open-domain Visual-Audio Generation with Diffusion Latent Aligners |
| topic | Computer Vision and Pattern Recognition Multimedia Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2402.17723 |