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.
Ahmed ElMahmoudy explores artificial intelligence and its ability to improve the lives of those with dementia and the visually impaired. Beyond this, his Talk highlights the ways AI can improve all human abilities and achieve the impossible. Ahmed is the co-founder of both ID Labs and EyeSense, where he researches the unique blend between art and technology to create solutions that enhance our daily life experiences and that extend our human capabilities. His work has earned him inclusion on the SE100’s list of Most Inspiring Social Innovations and Social Entrepreneurs in the world. This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at https://www.ted.com/tedx