# Urban Sound Propagation: a Benchmark for 1-Step Generative Modeling of Complex Physical Systems

arXiv: https://arxiv.org/abs/2403.10904 · HTML: https://mlsanity.com/paper/2403.10904/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 16 references that are in the map.
- First posted on arXiv 16 Mar 2024.

## Builds on (most cited first, 9 of 9)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [Physically Grounded Vision-Language Models for Robotic Manipulation](https://mlsanity.com/paper/2309.02561/) (2023)
- [Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling](https://mlsanity.com/paper/1710.11431/) (2017)
- [Deep Fluids: A Generative Network for Parameterized Fluid Simulations](https://mlsanity.com/paper/1806.02071/) (2018)
- [PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators](https://mlsanity.com/paper/2306.08918/) (2023)

## Built on by (most cited first, 2 of 2)

- [PhysicsGen: Can Generative Models Learn from Images to Predict Complex Physical Relations?](https://mlsanity.com/paper/2503.05333/) (2025)
- [Real-time Prediction of Urban Sound Propagation with Conditioned Normalizing Flows](https://mlsanity.com/paper/2510.04510/) (2025)

## Abstract (arXiv)

Data-driven modeling of complex physical systems is receiving a growing amount of attention in the simulation and machine learning communities. Since most physical simulations are based on compute-intensive, iterative implementations of differential equation systems, a (partial) replacement with learned, 1-step inference models has the potential for significant speedups in a wide range of application areas. In this context, we present a novel benchmark for the evaluation of 1-step generative learning models in terms of speed and physical correctness. Our Urban Sound Propagation benchmark is based on the physically complex and practically relevant, yet intuitively easy to grasp task of modeling the 2d propagation of waves from a sound source in an urban environment. We provide a dataset with 100k samples, where each sample consists of pairs of real 2d building maps drawn from OpenStreetmap, a parameterized sound source, and a simulated ground truth sound propagation for the given scene. The dataset provides four different simulation tasks with increasing complexity regarding reflection, diffraction and source variance. A first baseline evaluation of common generative U-Net, GAN and Diffusion models shows, that while these models are very well capable of modeling sound propagations in simple cases, the approximation of sub-systems represented by higher order equations systematically fails. Information about the dataset, download instructions and source codes are provided on our website: https://www.urban-sound-data.org.