View source for PBC:Image scaling/How it works

{| class="wikitable"
|+Comparison of scaling methods
! Original photo
! Upscaled 2x
! Upscaled 4x
! Upscaled 6x
! Algorithm and description
|-
|[[File:Markus Kage Paul Henry Serres Photography Original.jpg|thumb|600 × 863 reference]]
|[[File:Markus Kage Paul Henry Serres Photography Upscale 2x.jpg|thumb|1,200 × 1,726 (2x)]]
|[[File:Markus Kage Paul Henry Serres Photography Upscale 4x.jpg|thumb|2,400 × 3,452 (4x)]]
|[[File:Markus Kage Paul Henry Serres Photography Upscale 6x.jpg|thumb|3,600 × 5,178 (6x)]]
|Deep convolutional neural networks using perceptual loss. Developed on the basis of the super-resolution generative adversarial network (SRGAN) method, enhanced SRGAN (ESRGAN) is an incremental tweaking of the same generative adversarial network basis. Both methods rely on a perceptual loss function to evaluate training iterations.
|-
|[[File:Chad Driver Face Original.jpg|thumb|304 × 443 reference]]
|[[File:Chad Driver Face 2x.jpg|thumb|608 × 886 (2x)]]
|[[File:Chad Driver Face 4x.jpg|thumb|1,216 × 1,772 (4x)]]
|[[File:Chad Driver Face 6x.jpg|thumb|1,824 × 2,658 (6x)]]
|Deep convolutional neural networks. Using machine learning, convincing details are generated as best guesses by learning common patterns from a training data set. The upscaled result is sometimes described as a hallucination because the information introduced may not correspond to the content of the source. Enhanced deep residual network (EDSR) methods have been developed by optimizing conventional residual neural network architecture. Programs that use this method include waifu2x, Imglarger and Neural Enhance.
|}