Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Single Image Dehazing Using Scene Depth Ordering

Pengyang Ling, Huaian Chen, Xiao Tan, Yimeng Shan, Yi Jin

TL;DR

A depth order guided single image dehazing method, which utilizes depth order in hazy images to guide the dehazing process to achieve a similar depth perception in corresponding dehazing results, thereby bringing an overall improvement in restoration quality.

Abstract

Images captured in hazy weather generally suffer from quality degradation, and many dehazing methods have been developed to solve this problem. However, single image dehazing problem is still challenging due to its ill-posed nature. In this paper, we propose a depth order guided single image dehazing method, which utilizes depth order in hazy images to guide the dehazing process to achieve a similar depth perception in corresponding dehazing results. The consistency of depth perception ensures that the regions that look farther or closer in hazy images also appear farther or closer in the corresponding dehazing results, and thus effectively avoid the undesired visual effects. To achieve this goal, a simple yet effective strategy is proposed to extract the depth order in hazy images, which offers a reference for depth perception in hazy weather. Additionally, a depth order embedded transformation model is devised, which performs transmission estimation under the guidance of depth order to realize an unchanged depth order in the dehazing results. The extracted depth order provides a powerful global constraint for the dehazing process, which contributes to the efficient utilization of global information, thereby bringing an overall improvement in restoration quality. Extensive experiments demonstrate that the proposed method can better recover potential structure and vivid color with higher computational efficiency than the state-of-the-art dehazing methods.

Single Image Dehazing Using Scene Depth Ordering

TL;DR

A depth order guided single image dehazing method, which utilizes depth order in hazy images to guide the dehazing process to achieve a similar depth perception in corresponding dehazing results, thereby bringing an overall improvement in restoration quality.

Abstract

Images captured in hazy weather generally suffer from quality degradation, and many dehazing methods have been developed to solve this problem. However, single image dehazing problem is still challenging due to its ill-posed nature. In this paper, we propose a depth order guided single image dehazing method, which utilizes depth order in hazy images to guide the dehazing process to achieve a similar depth perception in corresponding dehazing results. The consistency of depth perception ensures that the regions that look farther or closer in hazy images also appear farther or closer in the corresponding dehazing results, and thus effectively avoid the undesired visual effects. To achieve this goal, a simple yet effective strategy is proposed to extract the depth order in hazy images, which offers a reference for depth perception in hazy weather. Additionally, a depth order embedded transformation model is devised, which performs transmission estimation under the guidance of depth order to realize an unchanged depth order in the dehazing results. The extracted depth order provides a powerful global constraint for the dehazing process, which contributes to the efficient utilization of global information, thereby bringing an overall improvement in restoration quality. Extensive experiments demonstrate that the proposed method can better recover potential structure and vivid color with higher computational efficiency than the state-of-the-art dehazing methods.
Paper Structure (21 sections, 1 theorem, 36 equations, 15 figures, 4 tables)

This paper contains 21 sections, 1 theorem, 36 equations, 15 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Prior-based Methods
  4. Data-driven Methods
  5. DEPTH ORDER IN DEHAZING PROCESS
  6. Motivation
  7. Depth Order Extraction
  8. Effectiveness Demonstration
  9. HAZE REMOVAL BASED ON DEPTH ORDER
  10. Transformation Model for Transmission Estimation
  11. Global Optimization Using Boundary Constraints
  12. Estimation for Atmospheric Light
  13. Image Restoration
  14. EXPERIMENTS
  15. Determination of Patch Size
  16. ...and 6 more sections

Key Result

Proposition 1

For every two pixels $({x_0},{y_0})$ and $({x_1},{y_1})$ with the order of $\theta _r^{haze}({x_0},{y_0}) \le \theta _r^{haze}({x_1},{y_1})$, the monotonically increasing weight function $\phi ( \cdot )$ is the sufficient condition for the results of Eq. (eq.19) to satisfy $\theta _r^{clear}({x_0},{

Figures (15)

  • Figure 1: The dehazing results of different methods on challenging real-world hazy scene.
  • Figure 2: The consistency of depth perception between the hazy image and the dehazing result of the proposed method.
  • Figure 3: Overview of the proposed method.
  • Figure 4: Examples of the relationship between $\theta ^{haze}(x,y)$ and scene depth in real-world hazy images. (a): Hazy images. (b):$\theta ^{haze}(x,y)$ obtained by Eq. (\ref{['eq.3']}). (c):$\theta _r^{haze}(x,y)$ obtained by Eqs. (\ref{['eq.3']}) and (\ref{['eq.12']}) with $r=35$. (d): The relationship between $\theta _r^{haze}(x,y)$ and scene depth under different patch sizes.
  • Figure 5: Frequency and cumulative density statistics of the $\rho$ values on 500 paired hazy images and ground-truth images.
  • ...and 10 more figures

Theorems & Definitions (1)

  • Proposition 1