C2MSNet: A Novel approach for single image haze removal

TL;DR

This paper introduces C2MSNet, a novel multi-stage neural network that fuses color information and estimates scene transmission to effectively remove haze from single images, outperforming existing methods.

Contribution

The paper proposes a new color fusion and multi-scale CNN approach for haze removal, addressing color distortion issues in poor illumination environments.

Findings

Outperforms existing state-of-the-art dehazing methods.

Achieves higher SSIM, MSE, and PSNR scores.

Effective in diverse haze conditions.

Abstract

Degradation of image quality due to the presence of haze is a very common phenomenon. Existing DehazeNet [3], MSCNN [11] tackled the drawbacks of hand crafted haze relevant features. However, these methods have the problem of color distortion in gloomy (poor illumination) environment. In this paper, a cardinal (red, green and blue) color fusion network for single image haze removal is proposed. In first stage, network fusses color information present in hazy images and generates multi-channel depth maps. The second stage estimates the scene transmission map from generated dark channels using multi channel multi scale convolutional neural network (McMs-CNN) to recover the original scene. To train the proposed network, we have used two standard datasets namely: ImageNet [5] and D-HAZY [1]. Performance evaluation of the proposed approach has been carried out using structural similarity index (SSIM), mean square error (MSE) and peak signal to noise ratio (PSNR). Performance analysis shows that the proposed approach outperforms the existing state-of-the-art methods for single image dehazing.