ROBUST REFLECTION REMOVAL BASED ON LIGHT FIELD IMAGING

Abstract

In daily photography, it is common to capture images in the reflection of an unwanted scene. This circumstance arises frequently when imaging through a semi-reflecting material such as glass. The unwanted reflection will affect the visibility of the background image and introduce ambiguity that perturbs the subsequent analysis on the image. It is a very challenging task to remove the reflection of an image since the problem is severely ill-posed. In this paper, we propose a novel algorithm to solve the reflection removal problem based on light field (LF) imaging. For the proposed algorithm, we first show that the strong gradient points of an LF epipolar plane image (EPI) are preserved after adding to the EPI of another LF image. We can then make use of these strong gradient points to give a rough estimation of the background and reflection. Rather than assuming that the background and reflection have absolutely different disparity ranges, we propose a sandwich layer model to allow them to have common disparities, which is more realistic in practical situations. Then, the background image is refined by recovering the components in the shared disparity range using an iterative enhancement process. Our experimental results show that the proposed algorithm achieves superior performance over traditional approaches both qualitatively and quantitatively. These results verify the robustness of the proposed algorithm when working with images captured from real-life scenes.

Existing System

LF epipolar plane image (EPI)

Proposed System

The main contributions of this paper are as follows:1) We explore the theoretical support of using LF EPI to estimate the disparities of the different layers of a superimposed LF image. We verify that if an LF image is formed by the superimposition of two LF image layers of different disparities, the EPI strong gradient points of both images will be at different positions of the combined EPI, and the gradient values will be preserved. 2) We propose a general sandwich model to describe the depth range of the background and reflection images. This model allows a shared depth range for both images, which is more realistic in practical situations. Following this model, the proposed method does not require the background and reflection images to have absolutely different depth ranges as in the existing approach. 3) We develop a new method to detect and extract the components of the background images that have the same disparities as the reflection. It is achieved based on an observation that these components can be found in both the initial background estimate and its residue.

Architecture

BLOCK DIAGRAM