Single Image Reflection Separation with Perceptual Losses
This addresses the problem of image quality degradation due to reflections for applications in photography and computer vision, representing an incremental improvement over existing methods.
The authors tackled the problem of separating reflection from a single image using a fully convolutional network trained with perceptual losses, achieving state-of-the-art performance in PSNR, SSIM, and perceptual user studies.
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.