Fast Single Image Reflection Suppression via Convex Optimization

TL;DR

This paper introduces a convex optimization-based method for removing reflections from single images, improving image quality efficiently for aesthetic and machine learning applications.

Contribution

It presents a novel convex model with a PDE and gradient thresholding, solved efficiently via Discrete Cosine Transform, for reflection suppression.

Findings

Effective reflection removal on synthetic and real images

Significant reduction in processing time

Achieves desirable suppression results

Abstract

Removing undesired reflections from images taken through the glass is of great importance in computer vision. It serves as a means to enhance the image quality for aesthetic purposes as well as to preprocess images in machine learning and pattern recognition applications. We propose a convex model to suppress the reflection from a single input image. Our model implies a partial differential equation with gradient thresholding, which is solved efficiently using Discrete Cosine Transform. Extensive experiments on synthetic and real-world images demonstrate that our approach achieves desirable reflection suppression results and dramatically reduces the execution time.