# A Light Dual-Task Neural Network for Haze Removal

## TL;DR

This paper introduces LDTNet, a lightweight neural network that simultaneously estimates transmission maps and removes haze from images in a single step, outperforming existing methods on synthetic and real-world data.

## Contribution

The paper presents a novel dual-task neural network that jointly performs haze removal and transmission map estimation, reducing reliance on artificial priors and improving generalization.

## Key findings

- Achieves superior haze removal performance compared to state-of-the-art methods.
- Effectively estimates transmission maps alongside haze removal in a single network.
- Demonstrates robustness on both synthetic and real-world images.

## Abstract

Single-image dehazing is a challenging problem due to its ill-posed nature. Existing methods rely on a suboptimal two-step approach, where an intermediate product like a depth map is estimated, based on which the haze-free image is subsequently generated using an artificial prior formula. In this paper, we propose a light dual-task Neural Network called LDTNet that restores the haze-free image in one shot. We use transmission map estimation as an auxiliary task to assist the main task, haze removal, in feature extraction and to enhance the generalization of the network. In LDTNet, the haze-free image and the transmission map are produced simultaneously. As a result, the artificial prior is reduced to the smallest extent. Extensive experiments demonstrate that our algorithm achieves superior performance against the state-of-the-art methods on both synthetic and real-world images.