Saved in:
Bibliographic Details
Main Authors: Wang, Junbo, Tan, Haofeng, Liao, Bowen, Jiang, Albert, Fei, Teng, Huang, Qixing, Zhou, Bing, Tu, Zhengzhong, Ye, Shan, Kang, Yuhao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.12734
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918360516657152
author Wang, Junbo
Tan, Haofeng
Liao, Bowen
Jiang, Albert
Fei, Teng
Huang, Qixing
Zhou, Bing
Tu, Zhengzhong
Ye, Shan
Kang, Yuhao
author_facet Wang, Junbo
Tan, Haofeng
Liao, Bowen
Jiang, Albert
Fei, Teng
Huang, Qixing
Zhou, Bing
Tu, Zhengzhong
Ye, Shan
Kang, Yuhao
contents Recent audio-to-image models have shown impressive performance in generating images of specific objects conditioned on their corresponding sounds. However, these models fail to reconstruct real-world landscapes conditioned on environmental soundscapes. To address this gap, we present Geo-contextual Soundscape-to-Landscape (GeoS2L) generation, a novel and practically significant task that aims to synthesize geographically realistic landscape images from environmental soundscapes. To support this task, we construct two large-scale geo-contextual multi-modal datasets, SoundingSVI and SonicUrban, which pair diverse environmental soundscapes with real-world landscape images. We propose SounDiT, a diffusion transformer (DiT)-based model that incorporates environmental soundscapes and geo-contextual scene conditioning to synthesize geographically coherent landscape images. Furthermore, we propose the Place Similarity Score (PSS), a practically-informed geo-contextual evaluation framework to measure consistency between input soundscapes and generated landscape images. Extensive experiments demonstrate that SounDiT outperforms existing baselines in the GeoS2L, while the PSS effectively captures multi-level generation consistency across element, scene,and human perception. Project page: https://gisense.github.io/SounDiT-Page/
format Preprint
id arxiv_https___arxiv_org_abs_2505_12734
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SounDiT: Geo-Contextual Soundscape-to-Landscape Generation
Wang, Junbo
Tan, Haofeng
Liao, Bowen
Jiang, Albert
Fei, Teng
Huang, Qixing
Zhou, Bing
Tu, Zhengzhong
Ye, Shan
Kang, Yuhao
Sound
Artificial Intelligence
Graphics
Human-Computer Interaction
Audio and Speech Processing
Recent audio-to-image models have shown impressive performance in generating images of specific objects conditioned on their corresponding sounds. However, these models fail to reconstruct real-world landscapes conditioned on environmental soundscapes. To address this gap, we present Geo-contextual Soundscape-to-Landscape (GeoS2L) generation, a novel and practically significant task that aims to synthesize geographically realistic landscape images from environmental soundscapes. To support this task, we construct two large-scale geo-contextual multi-modal datasets, SoundingSVI and SonicUrban, which pair diverse environmental soundscapes with real-world landscape images. We propose SounDiT, a diffusion transformer (DiT)-based model that incorporates environmental soundscapes and geo-contextual scene conditioning to synthesize geographically coherent landscape images. Furthermore, we propose the Place Similarity Score (PSS), a practically-informed geo-contextual evaluation framework to measure consistency between input soundscapes and generated landscape images. Extensive experiments demonstrate that SounDiT outperforms existing baselines in the GeoS2L, while the PSS effectively captures multi-level generation consistency across element, scene,and human perception. Project page: https://gisense.github.io/SounDiT-Page/
title SounDiT: Geo-Contextual Soundscape-to-Landscape Generation
topic Sound
Artificial Intelligence
Graphics
Human-Computer Interaction
Audio and Speech Processing
url https://arxiv.org/abs/2505.12734