# Unsupervised Single Image Dehazing Using Dark Channel Prior Loss

## TL;DR

This paper introduces an unsupervised deep learning approach for single image dehazing that directly minimizes the Dark Channel Prior energy function on real-world outdoor images, avoiding synthetic data.

## Contribution

It presents a novel unsupervised training method for dehazing that improves upon traditional prior-based methods by leveraging deep neural networks without requiring paired hazy and clear images.

## Key findings

- Performs comparably to supervised methods on dehazing tasks.
- Improves results of the Dark Channel Prior through learning-based regularization.
- Operates effectively on real-world outdoor images without synthetic training data.

## Abstract

Single image dehazing is a critical stage in many modern-day autonomous vision applications. Early prior-based methods often involved a time-consuming minimization of a hand-crafted energy function. Recent learning-based approaches utilize the representational power of deep neural networks (DNNs) to learn the underlying transformation between hazy and clear images. Due to inherent limitations in collecting matching clear and hazy images, these methods resort to training on synthetic data; constructed from indoor images and corresponding depth information. This may result in a possible domain shift when treating outdoor scenes. We propose a completely unsupervised method of training via minimization of the well-known, Dark Channel Prior (DCP) energy function. Instead of feeding the network with synthetic data, we solely use real-world outdoor images and tune the network's parameters by directly minimizing the DCP. Although our "Deep DCP" technique can be regarded as a fast approximator of DCP, it actually improves its results significantly. This suggests an additional regularization obtained via the network and learning process. Experiments show that our method performs on par with large-scale supervised methods.