Latest revision as of 21:24, 3 February 2021

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.

Comment: Appeared at ICCV'17 (International Conference on Computer Vision)

Original document

The different versions of the original document can be found in:

• http://arxiv.org/abs/1708.03474

• http://arxiv.org/pdf/1708.03474

• http://xplorestaging.ieee.org/ielx7/8234942/8237262/08237613.pdf?arnumber=8237613,

http://dx.doi.org/10.1109/iccv.2017.351

• https://dblp.uni-trier.de/db/conf/iccv/iccv2017.html#FanYHCW17,

https://arxiv.org/pdf/1708.03474.pdf,

https://arxiv.org/abs/1708.03474,

https://ieeexplore.ieee.org/document/8237613,

http://ieeexplore.ieee.org/document/8237613,

https://doi.org/10.1109/ICCV.2017.351,

https://academic.microsoft.com/#/detail/2963676366