Enhancing Photorealism Enhancement

We present an approach to enhancing the realism of synthetic images. The images are enhanced by a convolutional network that leverages intermediate representations produced by conventional rendering pipelines. The network is trained via a novel adversarial objective, which provides strong supervision at multiple perceptual levels. To address this we propose a new strategy for sampling image patches during training. We also introduce multiple architectural improvements in the deep network modules used for photorealism enhancement. The modifications by our method are geometrically and semantically consistent with the original images. Images from this dataset are recorded around the world with wide variety of cameras.