Enhancing Photorealism Enhancement

By Stephan R. Richter, Hassan Abu Alhaija, Vladlen Koltun. 2021

132 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Hongyang Li
2. Kashyap Chitta
3. Axel Sauer
4. Cheston Tan
5. Andreas Geiger
6. Li Chen
7. Jiafei Duan
8. Samson Yu

Citations in the corpus

• Projected GANs Converge Faster (2021, background): “While combining pretrained perceptual networks [58] with GANs for image-to-image translation has led to impressive results [14, 49, 59, 64], this idea has not yet materialized for unconditional noise-to-image synthesis.”
• A Survey of Embodied AI: From Simulators to Research Tasks (2021, background): “We believe that advances in 3D reconstruction techniques and physics engines [117]– [119] will improve the realism of embodied AI.”
• End-to-End Autonomous Driving: Challenges and Frontiers (2023, background): “Another approach to data-driven sensor simulationisdomainadaptation,whichaimstominimizethegap between real and graphics-based simulated sensor data [119].”