A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing

TL;DR

This paper introduces a versatile deep neural network architecture that leverages edge information for effective single image reflection removal and image smoothing, outperforming existing methods in accuracy and speed.

Contribution

The proposed approach uniquely estimates edges and reconstructs images without handcrafted components, applying a transferable pipeline to multiple low-level vision tasks.

Findings

Outperforms previous methods in reflection removal and image smoothing.

Achieves state-of-the-art quantitative and qualitative results.

Simple, fast, and easily transferable framework.

Abstract

This paper proposes a deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering. Unlike most other deep learning strategies applied in this context, our approach tackles these challenging problems by estimating edges and reconstructing images using only cascaded convolutional layers arranged such that no handcrafted or application-specific image-processing components are required. We apply the resulting transferrable pipeline to two different problem domains that are both sensitive to edges, namely, single image reflection removal and image smoothing. For the former, using a mild reflection smoothness assumption and a novel synthetic data generation method that acts as a type of weak supervision, our network is able to solve much more difficult reflection cases that cannot be handled by previous methods. For the latter, we also exceed the state-of-the-art quantitative and qualitative results by wide margins. In all cases, the proposed framework is simple, fast, and easy to transfer across disparate domains.