Previous Article in Journal
Hybrid Deep Learning Models for Arabic Sign Language Recognition in Healthcare Applications
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
BDCC
Volume 9
Issue 11
10.3390/bdcc9110282
BDCC-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Pixel-Dehaze: Deciphering Dehazing Through Regression-Based Depth and Scattering Estimation

by
Vaibhav Baldeva
1,
Vishakha Sharma
1,
Satakshi Verma
1,
Priya Kansal
1,
Sachin Kansal
1 and
Jyotindra Narayan
2,*
1
Computer Science Engineering Department, Thapar Institute of Engineering Technology, Patiala 147004, Punjab, India
2
Department of Mechanical Engineering, Indian Institute of Technology, Patna 801106, Bihar, India
*
Author to whom correspondence should be addressed.
Big Data Cogn. Comput. 2025, 9(11), 282; https://doi.org/10.3390/bdcc9110282 (registering DOI)
Submission received: 20 September 2025 / Revised: 1 November 2025 / Accepted: 4 November 2025 / Published: 8 November 2025
Versions Notes

Abstract

Haze significantly reduces visibility in critical applications such as autonomous driving, surveillance, and firefighting, making its removal essential for safety and reliability. Motivated by the limited robustness of the existing methods under non-uniform haze conditions, this study introduces a novel regression-based dehazing model that simultaneously incorporates the atmospheric light constant, transmission map, and scattering coefficient for improved restoration. Instead of relying on complex deep networks, the model leverages brightness–saturation cues and regression-driven scattering estimation with localized haze detection to reconstruct clearer images efficiently. Evaluated on the RESIDE dataset, the approach consistently surpasses state-of-the-art techniques including Dark Channel Prior, AOD-Net, FFA-Net, and Single U-Net, achieving SSIM = 0.99, PSNR = 22.25 dB, VIF = 1.08, and the lowest processing time of 0.038 s, demonstrating both accuracy and practicality for real-world deployment.
Keywords: image dehazing; regression-based model; brightness–saturation features; atmospheric light estimation; transmission map; localized haze detection; real-time image restoration image dehazing; regression-based model; brightness–saturation features; atmospheric light estimation; transmission map; localized haze detection; real-time image restoration

Share and Cite

MDPI and ACS Style

Baldeva, V.; Sharma, V.; Verma, S.; Kansal, P.; Kansal, S.; Narayan, J. Pixel-Dehaze: Deciphering Dehazing Through Regression-Based Depth and Scattering Estimation. Big Data Cogn. Comput. 2025, 9, 282. https://doi.org/10.3390/bdcc9110282

AMA Style

Baldeva V, Sharma V, Verma S, Kansal P, Kansal S, Narayan J. Pixel-Dehaze: Deciphering Dehazing Through Regression-Based Depth and Scattering Estimation. Big Data and Cognitive Computing. 2025; 9(11):282. https://doi.org/10.3390/bdcc9110282

Chicago/Turabian Style

Baldeva, Vaibhav, Vishakha Sharma, Satakshi Verma, Priya Kansal, Sachin Kansal, and Jyotindra Narayan. 2025. "Pixel-Dehaze: Deciphering Dehazing Through Regression-Based Depth and Scattering Estimation" Big Data and Cognitive Computing 9, no. 11: 282. https://doi.org/10.3390/bdcc9110282

APA Style

Baldeva, V., Sharma, V., Verma, S., Kansal, P., Kansal, S., & Narayan, J. (2025). Pixel-Dehaze: Deciphering Dehazing Through Regression-Based Depth and Scattering Estimation. Big Data and Cognitive Computing, 9(11), 282. https://doi.org/10.3390/bdcc9110282

Article Metrics

Back to TopTop