From synthetic to natural — single natural image dehazing deep networks using synthetic dataset domain randomization

Shamsuddin, Abdul Fathaah; Ragunathan, Krupasankari; Abhijith, P.; P.M., Deepak Raja Sekar; Sankaran, Praveen

doi:10.1016/j.jvcir.2022.103636

Cited by 4 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dehazing techniques play a vital role in various real-world applications, including surveillance, autonomous vehicles, remote sensing, and outdoor photography, where visibility is often compromised due to weather conditions or pollution [2]. The physical process of haze formation occurs due to the scattering and absorption of light by particles and molecules present in the atmosphere [3]. Light rays from objects in the scene interact with these particles, leading to multiple scattering events, which, in turn, result in the loss of image details and degradation of visual quality.…”

Section: Introductionmentioning

confidence: 99%

DSSCNet: Deep Custom Spatial and Spectral Consistency Layer-Based Dehazing Network

Kaur,

Singh,

Kumar

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Poor weather conditions, such as haze, fog, and smog, present significant challenges in capturing clear and visually appealing images. To address this issue, we propose a Deep Custom Spatial and Spectral Consistency Layer-based Dehazing Network (DSSCNet) that effectively removes haze from images while preserving important spatial and spectral details. The network architecture includes a custom Haze Removal Layer (HRL), convolutional layers with ReLU activation, pooling layers, skip connections, and a custom Spatial and Spectral Consistency Layer (cSSCL). HRL estimates atmospheric light and transmission maps to generate an intermediate haze-free image. The proposed loss function combines Mean Squared Error (MSE) loss with a Consistency Loss (CL) to encourage content preservation during dehazing. The network is trained using the Adam optimizer to optimize the loss function, resulting in a powerful dehazing network capable of producing visually realistic and haze-free images. Extensive experimental results demonstrate the effectiveness and superiority of DSSCNet when compared to existing dehazing techniques. The outcomes highlight that DSSCNet outperforms competitive models in terms of various performance metrics, including Contrast gain (c g ), new visible edges (e), new edge gradients (r), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM). These improvements amount to an average enhancement of around 1.27%, 1.12%, 1.18%, 1.21%, and 1.24%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%