# SounDiT: Geo-Contextual Soundscape-to-Landscape Generation

Source: [SounDiT: Geo-Contextual Soundscape-to-Landscape Generation](<https://www.sota2.com/research/paper/68fa789b1e209131cea79499>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-04T05:00:05.078Z

Authors: Junbo Wang, Haofeng Tan, Bowen Liao, Albert Jiang, Teng Fei, Qixing Huang, Bing Zhou, Zhengzhong Tu, Shan Ye, Yuhao Kang

Published: 2025-05-19T05:47:13.000Z

## Abstract

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/

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Soundscape-to-image generation on SoundingSVI 169K](<https://www.sota2.com/research/sota/soundscape-to-image-generation-on-soundingsvi-169k.md>): Soundscape-to-image generation; SoundingSVI 169K; FID: 16.839.

- [Soundscape-to-image generation on SonicUrban 237K](<https://www.sota2.com/research/sota/soundscape-to-image-generation-on-sonicurban-237k.md>): Soundscape-to-image generation; SonicUrban 237K; FID: 11.553.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.12734>)

[PDF](<https://arxiv.org/pdf/2505.12734.pdf>)