Work

Single Image Reflection Separation with Perceptual Losses

Year: 2018
Type: conference-paper
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.
Language: English
Open Access status: green
Funder: Nvidia
OpenAlex ID: W2798966709
FWCI: 9.693
Cites: 38
Cited by: 410
Related to: 10