Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lee, Junwon, Im, Jaekwon, Kim, Dabin, Nam, Juhan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918142703304704
author Lee, Junwon
Im, Jaekwon
Kim, Dabin
Nam, Juhan
author_facet Lee, Junwon
Im, Jaekwon
Kim, Dabin
Nam, Juhan
contents Foley sound synthesis is crucial for multimedia production, enhancing user experience by synchronizing audio and video both temporally and semantically. Recent studies on automating this labor-intensive process through video-to-sound generation face significant challenges. Systems lacking explicit temporal features suffer from poor alignment and controllability, while timestamp-based models require costly and subjective human annotation. We propose Video-Foley, a video-to-sound system using Root Mean Square (RMS) as an intuitive condition with semantic timbre prompts (audio or text). RMS, a frame-level intensity envelope closely related to audio semantics, acts as a temporal event feature to guide audio generation from video. The annotation-free self-supervised learning framework consists of two stages, Video2RMS and RMS2Sound, incorporating novel ideas including RMS discretization and RMS-ControlNet with a pretrained text-to-audio model. Our extensive evaluation shows that Video-Foley achieves state-of-the-art performance in audio-visual alignment and controllability for sound timing, intensity, timbre, and nuance. Source code, model weights and demos are available on our companion website. (https://jnwnlee.github.io/video-foley-demo)
format Preprint
id arxiv_https___arxiv_org_abs_2408_11915
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound
Lee, Junwon
Im, Jaekwon
Kim, Dabin
Nam, Juhan
Sound
Computer Vision and Pattern Recognition
Machine Learning
Multimedia
Audio and Speech Processing
Foley sound synthesis is crucial for multimedia production, enhancing user experience by synchronizing audio and video both temporally and semantically. Recent studies on automating this labor-intensive process through video-to-sound generation face significant challenges. Systems lacking explicit temporal features suffer from poor alignment and controllability, while timestamp-based models require costly and subjective human annotation. We propose Video-Foley, a video-to-sound system using Root Mean Square (RMS) as an intuitive condition with semantic timbre prompts (audio or text). RMS, a frame-level intensity envelope closely related to audio semantics, acts as a temporal event feature to guide audio generation from video. The annotation-free self-supervised learning framework consists of two stages, Video2RMS and RMS2Sound, incorporating novel ideas including RMS discretization and RMS-ControlNet with a pretrained text-to-audio model. Our extensive evaluation shows that Video-Foley achieves state-of-the-art performance in audio-visual alignment and controllability for sound timing, intensity, timbre, and nuance. Source code, model weights and demos are available on our companion website. (https://jnwnlee.github.io/video-foley-demo)
title Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition For Foley Sound
topic Sound
Computer Vision and Pattern Recognition
Machine Learning
Multimedia
Audio and Speech Processing
url https://arxiv.org/abs/2408.11915