Beyond Descriptions: A Generative Scene2Audio Framework for Blind and Low-Vision Users to Experience Vista Landscapes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gupta, Chitralekha, Peng, Jing, Ram, Ashwin, Sridhar, Shreyas, Jouffrais, Christophe, Nanayakkara, Suranga
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918414613741568
author Gupta, Chitralekha
Peng, Jing
Ram, Ashwin
Sridhar, Shreyas
Jouffrais, Christophe
Nanayakkara, Suranga
author_facet Gupta, Chitralekha
Peng, Jing
Ram, Ashwin
Sridhar, Shreyas
Jouffrais, Christophe
Nanayakkara, Suranga
contents Current scene perception tools for Blind and Low Vision (BLV) individuals rely on spoken descriptions but lack engaging representations of visually pleasing distant environmental landscapes (Vista spaces). Our proposed Scene2Audio framework generates comprehensible and enjoyable nonverbal audio using generative models informed by psychoacoustics, and principles of scene audio composition. Through a user study with 11 BLV participants, we found that combining the Scene2Audio sounds with speech creates a better experience than speech alone, as the sound effects complement the speech making the scene easier to imagine. A mobile app "in-the-wild" study with 7 BLV users for more than a week further showed the potential of Scene2Audio in enhancing outdoor scene experiences. Our work bridges the gap between visual and auditory scene perception by moving beyond purely descriptive aids, addressing the aesthetic needs of BLV users.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27295
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Descriptions: A Generative Scene2Audio Framework for Blind and Low-Vision Users to Experience Vista Landscapes
Gupta, Chitralekha
Peng, Jing
Ram, Ashwin
Sridhar, Shreyas
Jouffrais, Christophe
Nanayakkara, Suranga
Human-Computer Interaction
Artificial Intelligence
Current scene perception tools for Blind and Low Vision (BLV) individuals rely on spoken descriptions but lack engaging representations of visually pleasing distant environmental landscapes (Vista spaces). Our proposed Scene2Audio framework generates comprehensible and enjoyable nonverbal audio using generative models informed by psychoacoustics, and principles of scene audio composition. Through a user study with 11 BLV participants, we found that combining the Scene2Audio sounds with speech creates a better experience than speech alone, as the sound effects complement the speech making the scene easier to imagine. A mobile app "in-the-wild" study with 7 BLV users for more than a week further showed the potential of Scene2Audio in enhancing outdoor scene experiences. Our work bridges the gap between visual and auditory scene perception by moving beyond purely descriptive aids, addressing the aesthetic needs of BLV users.
title Beyond Descriptions: A Generative Scene2Audio Framework for Blind and Low-Vision Users to Experience Vista Landscapes
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2603.27295