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

By Qingnan Fan, Jiaolong Yang, Gang Hua, Baoquan Chen, David Paul Wipf. IEEE International Conference on Computer Vision, 2017

329 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/965922007192c818db103bcc3e500a10048e9e02

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Lu Yuan
2. Yujiu Yang
3. Weihao Xia
4. Ming-Hsuan Yang
5. Jing-Hao Xue
6. Dongdong Chen
7. Luc Van Gool
8. Xiaogang Wang

Citations in the corpus

• Cooperative Semantic Segmentation and Image Restoration in Adverse Environmental Conditions (2019, methodology): “For image synthesis, we use two methods to synthesis reflection images as in [44, 52, 11] with some modifications to make sure the size of obtained images is identical with those in [8].”
• Gated Context Aggregation Network for Image Dehazing and Deraining (2018, methodology): “As demonstrated in [10, 9], besides the input image, pre-calculating the edge of the input image and feeding them into the network as the auxiliary information is very helpful to the network learning.”
• Single Image Reflection Separation with Perceptual Losses (2018, methodology): “[5] recently propose a deep learning network, the Cascaded Edge and Image Learning Network (CEILNet), for reflection removal.”