Single Image Reflection Separation with Perceptual Losses

Abstract

We present an approach to separating reflection from a single image. The approach uses a fully convolutional network trained end-to-end with losses that exploit low-level and high-level image information. Our loss function includes two perceptual losses: a feature loss from a visual perception network, and an adversarial loss that encodes characteristics of images in the transmission layers. We also propose a novel exclusion loss that enforces pixel-level layer separation. We create a dataset of real-world images with reflection and corresponding ground-truth transmission layers for quantitative evaluation and model training. We validate our method through comprehensive quantitative experiments and show that our approach outperforms state-of-the-art reflection removal methods in PSNR, SSIM, and perceptual user study. We also extend our method to two other image enhancement tasks to demonstrate the generality of our approach.

9 pages, 8 figures, CVPR 2018

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Multi-Scale Context Aggregation by Dilated Convolutions
• Loss Functions for Neural Networks for Image Processing
• Fast Image Processing with Fully-Convolutional Networks
• Reflection Separation Using Guided Annotation

Cited by in corpus (5)

• Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
• Polarized Reflection Removal with Perfect Alignment in the Wild
• Semantic Image Matting
• Controllable Attention for Structured Layered Video Decomposition
• ReflectNet -- A Generative Adversarial Method for Single Image Reflection Suppression