Abstract

In this paper we present a new method for estimating the optical transmission in hazy scenes given a single input image. Based on this estimation, the scattered light is eliminated to increase scene visibility and recover haze-free scene contrasts. In this new approach we formulate a refined image formation model that accounts for surface shading in addition to the transmission function. This allows us to resolve ambiguities in the data by searching for a solution in which the resulting shading and transmission functions are locally statistically uncorrelated. A similar principle is used to estimate the color of the haze. Results demonstrate the new method abilities to remove the haze layer as well as provide a reliable transmission estimate which can be used for additional applications such as image refocusing and novel view synthesis.

Keywords:
Visibility Haze Computer science Transmission (telecommunications) Computer vision Artificial intelligence Image (mathematics) Image formation Function (biology) Shading Computer graphics (images) Optics Geography Telecommunications Physics

Metrics

369
Cited By
17.96
FWCI (Field Weighted Citation Impact)
26
Refs
1.00
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Image Enhancement Techniques
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition
Advanced Vision and Imaging
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition
Advanced Image Processing Techniques
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition

Related Documents

JOURNAL ARTICLE

Single image dehazing

Raanan Fattal

Journal:   ACM Transactions on Graphics Year: 2008 Vol: 27 (3)Pages: 1-9
BOOK-CHAPTER

Single-Image Dehazing

Jiandong Tian

Research on intelligent manufacturing Year: 2021 Pages: 229-270
JOURNAL ARTICLE

Robust Single-Image Dehazing

Changwon Kim

Journal:   Electronics Year: 2021 Vol: 10 (21)Pages: 2636-2636
BOOK-CHAPTER

Single Image Dehazing via Image Generating

Shengdong ZhangJian YaoEdel García-Reyes

Lecture notes in computer science Year: 2018 Pages: 123-136
BOOK-CHAPTER

Single Image Dehazing Using CNN

Samarth BhadaneRanjeet Vasant BidweBhushan Zope

Lecture notes in electrical engineering Year: 2024 Pages: 387-395
© 2026 ScienceGate Book Chapters — All rights reserved.