# Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understanding

## TL;DR

This paper introduces CMAda, a curriculum-based method for adapting semantic segmentation models from synthetic to real foggy scenes, complemented by new fog simulation, density estimation, and densification techniques, along with a new foggy dataset.

## Contribution

The paper presents a novel curriculum model adaptation approach for foggy scene understanding, along with new methods for synthetic fog generation, fog density estimation, and fog densification, plus a new real fog dataset.

## Key findings

- CMAda significantly improves semantic foggy scene understanding performance.
- The proposed fog simulation and density estimation outperform existing methods.
- The Foggy Zurich dataset provides valuable real foggy images with annotations.

## Abstract

This work addresses the problem of semantic scene understanding under fog. Although marked progress has been made in semantic scene understanding, it is mainly concentrated on clear-weather scenes. Extending semantic segmentation methods to adverse weather conditions such as fog is crucial for outdoor applications. In this paper, we propose a novel method, named Curriculum Model Adaptation (CMAda), which gradually adapts a semantic segmentation model from light synthetic fog to dense real fog in multiple steps, using both labeled synthetic foggy data and unlabeled real foggy data. The method is based on the fact that the results of semantic segmentation in moderately adverse conditions (light fog) can be bootstrapped to solve the same problem in highly adverse conditions (dense fog). CMAda is extensible to other adverse conditions and provides a new paradigm for learning with synthetic data and unlabeled real data. In addition, we present three other main stand-alone contributions: 1) a novel method to add synthetic fog to real, clear-weather scenes using semantic input; 2) a new fog density estimator; 3) a novel fog densification method to densify the fog in real foggy scenes without using depth; and 4) the Foggy Zurich dataset comprising 3808 real foggy images, with pixel-level semantic annotations for 40 images under dense fog. Our experiments show that 1) our fog simulation and fog density estimator outperform their state-of-the-art counterparts with respect to the task of semantic foggy scene understanding (SFSU); 2) CMAda improves the performance of state-of-the-art models for SFSU significantly, benefiting both from our synthetic and real foggy data. The datasets and code are available at the project website.