Multi-Scale Boosted Dehazing Network with Dense Feature Fusion

TL;DR

This paper introduces a novel multi-scale dehazing network that combines boosting strategies and dense feature fusion to effectively restore haze-free images, outperforming existing methods on benchmark datasets.

Contribution

It proposes a multi-scale boosted dehazing network with a dense feature fusion module based on U-Net, integrating error feedback and spatial information preservation techniques.

Findings

Outperforms state-of-the-art dehazing methods on benchmark datasets.

Effectively preserves spatial details in hazy images.

Demonstrates robustness on real-world hazy images.

Abstract

In this paper, we propose a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion based on the U-Net architecture. The proposed method is designed based on two principles, boosting and error feedback, and we show that they are suitable for the dehazing problem. By incorporating the Strengthen-Operate-Subtract boosting strategy in the decoder of the proposed model, we develop a simple yet effective boosted decoder to progressively restore the haze-free image. To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme. We show that the dense feature fusion module can simultaneously remedy the missing spatial information from high-resolution features and exploit the non-adjacent features. Extensive evaluations demonstrate that the proposed model performs favorably against the state-of-the-art approaches on the benchmark datasets as well as real-world hazy images.