# Semantic Understanding of Foggy Scenes with Purely Synthetic Data

arXiv: https://arxiv.org/abs/1910.03997 · HTML: https://mlsanity.com/paper/1910.03997/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2019.

## Built on by (most cited first, 22 of 22)

- [Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather](https://mlsanity.com/paper/2108.05249/) (2021)
- [ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Field](https://mlsanity.com/paper/2211.13226/) (2022)
- [Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding](https://mlsanity.com/paper/2112.00484/) (2021)
- [Benchmarking the Robustness of LiDAR Semantic Segmentation Models](https://mlsanity.com/paper/2301.00970/) (2023)
- [Analyzing Infrastructure LiDAR Placement with Realistic LiDAR Simulation Library](https://mlsanity.com/paper/2211.15975/) (2022)
- [Let Segment Anything Help Image Dehaze](https://mlsanity.com/paper/2306.15870/) (2023)
- [RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting](https://mlsanity.com/paper/2503.21442/) (2025)
- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [WeatherEdit: Controllable Weather Editing with 4D Gaussian Field](https://mlsanity.com/paper/2505.20471/) (2025)
- [Controllable Weather Synthesis and Removal with Video Diffusion Models](https://mlsanity.com/paper/2505.00704/) (2025)
- [SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving](https://mlsanity.com/paper/2403.17094/) (2024)
- [Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion](https://mlsanity.com/paper/2206.04879/) (2022)
- [SurroundNet: Towards Effective Low-Light Image Enhancement](https://mlsanity.com/paper/2110.05098/) (2021)
- [FogAdapt: Self-Supervised Domain Adaptation for Semantic Segmentation of Foggy Images](https://mlsanity.com/paper/2201.02588/) (2022)
- [HazeCLIP: Towards Language Guided Real-World Image Dehazing](https://mlsanity.com/paper/2407.13719/) (2024)
- [DeepIPC: Deeply Integrated Perception and Control for an Autonomous Vehicle in Real Environments](https://mlsanity.com/paper/2207.09934/) (2022)
- [RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions](https://mlsanity.com/paper/2109.01820/) (2021)
- [ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions](https://mlsanity.com/paper/2506.15837/) (2025)
- [Robustness of Object Detection of Autonomous Vehicles in Adverse Weather Conditions](https://mlsanity.com/paper/2602.12902/) (2026)
- [Semantic-Aware, Physics-Informed, Geometry-Grounded Weather Video Synthesis](https://mlsanity.com/paper/2606.29020/) (2026)
- [OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation](https://mlsanity.com/paper/2410.11536/) (2024)
- [Reproducing and Extending RaDelft 4D Radar with Camera-Assisted Labels](https://mlsanity.com/paper/2512.02394/) (2025)

## Abstract (arXiv)

This work addresses the problem of semantic scene understanding under foggy road conditions. Although marked progress has been made in semantic scene understanding over the recent years, it is mainly concentrated on clear weather outdoor scenes. Extending semantic segmentation methods to adverse weather conditions like fog is crucially important for outdoor applications such as self-driving cars. In this paper, we propose a novel method, which uses purely synthetic data to improve the performance on unseen real-world foggy scenes captured in the streets of Zurich and its surroundings. Our results highlight the potential and power of photo-realistic synthetic images for training and especially fine-tuning deep neural nets. Our contributions are threefold, 1) we created a purely synthetic, high-quality foggy dataset of 25,000 unique outdoor scenes, that we call Foggy Synscapes and plan to release publicly 2) we show that with this data we outperform previous approaches on real-world foggy test data 3) we show that a combination of our data and previously used data can even further improve the performance on real-world foggy data.