HOME REVIEWS CONTACT NEWS ARCHIV

Enhancing Photorealism Enhancement


Enhancing Photorealism Enhancement Stephan R. Richter, Hassan Abu AlHaija, and Vladlen Koltun Paper: https://arxiv.org/abs/2105.04619 Code and data: https://github.com/intel-isl/PhotorealismEnhancement Project page: https://intel-isl.github.io/PhotorealismEnhancement/ 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. We analyze scene layout distributions in commonly used datasets and find that they differ in important ways. We hypothesize that this is one of the causes of strong artifacts that can be observed in the results of many prior methods. 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. We confirm the benefits of our contributions in controlled experiments and report substantial gains in stability and realism in comparison to recent image-to-image translation methods and a variety of other baselines.

Bilder: Intel ISL







Content Copyright (c) 1995-2021 GAMEFRONT Frank Michaelis, GAMEFRONT Online. All Rights Reserved. Redistribution of GAMEFRONT Content in part or in whole without prior written content is a violation of federal copyright law. All referenced company names, characters and trademarks are registered trademarks or copyrights of their respective owners. [Hinweis / Impressum / Nutzungshinweise] [Datenschutzerklärung]