MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hayakawa, Akio, Ishii, Masato, Shibuya, Takashi, Mitsufuji, Yuki
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912244859666432
author Hayakawa, Akio
Ishii, Masato
Shibuya, Takashi
Mitsufuji, Yuki
author_facet Hayakawa, Akio
Ishii, Masato
Shibuya, Takashi
Mitsufuji, Yuki
contents This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal models to cooperatively generate well-aligned samples across modalities. Specifically, given two pre-trained base diffusion models, we train a lightweight joint guidance module to adjust scores separately estimated by the base models to match the score of joint distribution over audio and video. We show that this guidance can be computed using the gradient of the optimal discriminator, which distinguishes real audio-video pairs from fake ones independently generated by the base models. Based on this analysis, we construct a joint guidance module by training this discriminator. Additionally, we adopt a loss function to stabilize the discriminator's gradient and make it work as a noise estimator, as in standard diffusion models. Empirical evaluations on several benchmark datasets demonstrate that our method improves both single-modal fidelity and multimodal alignment with relatively few parameters. The code is available at: https://github.com/SonyResearch/MMDisCo.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17842
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation
Hayakawa, Akio
Ishii, Masato
Shibuya, Takashi
Mitsufuji, Yuki
Computer Vision and Pattern Recognition
Machine Learning
Multimedia
Sound
Audio and Speech Processing
This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal models to cooperatively generate well-aligned samples across modalities. Specifically, given two pre-trained base diffusion models, we train a lightweight joint guidance module to adjust scores separately estimated by the base models to match the score of joint distribution over audio and video. We show that this guidance can be computed using the gradient of the optimal discriminator, which distinguishes real audio-video pairs from fake ones independently generated by the base models. Based on this analysis, we construct a joint guidance module by training this discriminator. Additionally, we adopt a loss function to stabilize the discriminator's gradient and make it work as a noise estimator, as in standard diffusion models. Empirical evaluations on several benchmark datasets demonstrate that our method improves both single-modal fidelity and multimodal alignment with relatively few parameters. The code is available at: https://github.com/SonyResearch/MMDisCo.
title MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation
topic Computer Vision and Pattern Recognition
Machine Learning
Multimedia
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2405.17842