Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kang, Minjae, Brandão, Martim
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915258585579520
author Kang, Minjae
Brandão, Martim
author_facet Kang, Minjae
Brandão, Martim
contents Recent audio-visual generative models have made substantial progress in generating images from audio. However, existing approaches focus on generating images from single-class audio and fail to generate images from mixed audio. To address this, we propose an Audio-Visual Generation and Separation model (AV-GAS) for generating images from soundscapes (mixed audio containing multiple classes). Our contribution is threefold: First, we propose a new challenge in the audio-visual generation task, which is to generate an image given a multi-class audio input, and we propose a method that solves this task using an audio-visual separator. Second, we introduce a new audio-visual separation task, which involves generating separate images for each class present in a mixed audio input. Lastly, we propose new evaluation metrics for the audio-visual generation task: Class Representation Score (CRS) and a modified R@K. Our model is trained and evaluated on the VGGSound dataset. We show that our method outperforms the state-of-the-art, achieving 7% higher CRS and 4% higher R@2* in generating plausible images with mixed audio.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18283
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator
Kang, Minjae
Brandão, Martim
Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
Sound
Audio and Speech Processing
Recent audio-visual generative models have made substantial progress in generating images from audio. However, existing approaches focus on generating images from single-class audio and fail to generate images from mixed audio. To address this, we propose an Audio-Visual Generation and Separation model (AV-GAS) for generating images from soundscapes (mixed audio containing multiple classes). Our contribution is threefold: First, we propose a new challenge in the audio-visual generation task, which is to generate an image given a multi-class audio input, and we propose a method that solves this task using an audio-visual separator. Second, we introduce a new audio-visual separation task, which involves generating separate images for each class present in a mixed audio input. Lastly, we propose new evaluation metrics for the audio-visual generation task: Class Representation Score (CRS) and a modified R@K. Our model is trained and evaluated on the VGGSound dataset. We show that our method outperforms the state-of-the-art, achieving 7% higher CRS and 4% higher R@2* in generating plausible images with mixed audio.
title Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Multimedia
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2504.18283