Gated Fusion Network for Single Image Dehazing

TL;DR

This paper introduces a novel end-to-end neural network for single image dehazing that uses a fusion strategy of multiple processed inputs and confidence maps to produce clearer images, outperforming existing methods.

Contribution

The paper presents a new fusion-based neural network architecture with confidence-guided gating for improved single image dehazing, including a multi-scale training approach to reduce halo artifacts.

Findings

Outperforms state-of-the-art dehazing algorithms on synthetic images.

Effectively preserves visibility and reduces artifacts in real-world images.

Demonstrates robustness across diverse hazy conditions.

Abstract

In this paper, we propose an efficient algorithm to directly restore a clear image from a hazy input. The proposed algorithm hinges on an end-to-end trainable neural network that consists of an encoder and a decoder. The encoder is exploited to capture the context of the derived input images, while the decoder is employed to estimate the contribution of each input to the final dehazed result using the learned representations attributed to the encoder. The constructed network adopts a novel fusion-based strategy which derives three inputs from an original hazy image by applying White Balance (WB), Contrast Enhancing (CE), and Gamma Correction (GC). We compute pixel-wise confidence maps based on the appearance differences between these different inputs to blend the information of the derived inputs and preserve the regions with pleasant visibility. The final dehazed image is yielded by gating the important features of the derived inputs. To train the network, we introduce a multi-scale approach such that the halo artifacts can be avoided. Extensive experimental results on both synthetic and real-world images demonstrate that the proposed algorithm performs favorably against the state-of-the-art algorithms.