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

arXiv: https://arxiv.org/abs/2505.12734 · HTML: https://mlsanity.com/paper/2505.12734/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 100 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [VGGSound: A Large-scale Audio-Visual Dataset](https://mlsanity.com/paper/2004.14368/) (2020)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://mlsanity.com/paper/2405.08748/) (2024)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [Any-to-Any Generation via Composable Diffusion](https://mlsanity.com/paper/2305.11846/) (2023)
- [Visually Indicated Sounds](https://mlsanity.com/paper/1512.08512/) (2015)
- [Visual to Sound: Generating Natural Sound for Videos in the Wild](https://mlsanity.com/paper/1712.01393/) (2017)
- [ACAV100M: Automatic Curation of Large-Scale Datasets for Audio-Visual Video Representation Learning](https://mlsanity.com/paper/2101.10803/) (2021)
- [Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment](https://mlsanity.com/paper/2303.17490/) (2023)
- [AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation](https://mlsanity.com/paper/2406.07686/) (2024)
- [OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces](https://mlsanity.com/paper/2407.11895/) (2024)
- [BirdSet: A Large-Scale Dataset for Audio Classification in Avian Bioacoustics](https://mlsanity.com/paper/2403.10380/) (2024)
- [Sound-Guided Semantic Video Generation](https://mlsanity.com/paper/2204.09273/) (2022)
- [GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation](https://mlsanity.com/paper/2303.10056/) (2023)

## Abstract (arXiv)

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/