PofoliaShared via Pofolia

· 2017

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

Christian Ledig, Lucas Theis, Ferenc Huszár, José Caballero et al.

Short summary

SRGAN, a novel generative adversarial network, achieves photo-realistic single image super-resolution at 4x upscaling factors by using a perceptual loss function that combines adversarial and content losses.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Computer Vision and Pattern Recognition

Computer Vision and Pattern RecognitionComputer Science