Comparison gallery of image scaling algorithms

This gallery shows the results of numerous image scaling algorithms.

Scaling methods
An image size can be changed in several ways. Consider resizing a 160x160 pixel photo to the following 40x40 pixel thumbnail and then scaling the thumbnail to a 160x160 pixel image. Also consider doubling the size of the following image containing text.

{| class="wikitable" ! Original photo ! Upscaled thumbnail ! Upscaled text ! Algorithm and description
 * +Comparison of scaling methods
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * 40 by 40 thumbnail of 'Green Sea Shell' (x4 Nearest Neighbour).png
 * [[Image:Image-after-trivial-scaling.png|Nearest-neighbor interpolation]]
 * [[Image:Image-after-trivial-scaling.png|Nearest-neighbor interpolation]]

Nearest-neighbor interpolation
One of the simpler ways of increasing the size, replacing every pixel with a number of pixels of the same color. The resulting image is larger than the original, and preserves all the original detail, but has (possibly undesirable) jaggedness. The diagonal lines of the "W", for example, now show the "stairway" shape characteristic of nearest-neighbor interpolation. Other scaling methods below are better at preserving smooth contours in the image.
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * 40 by 40 thumbnail of 'Green Sea Shell' (x4 Bilinear).png
 * Image-after-linear-interpolation.png
 * Image-after-linear-interpolation.png

Bilinear interpolation
Linear (or bilinear, in two dimensions) interpolation is typically good for changing the size of an image, but causes some undesirable softening of details and can still be somewhat jagged.
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * 40 by 40 thumbnail of 'Green Sea Shell' (x4 Bicubic).png
 * Image-after-cubic-interpolation.png
 * Image-after-cubic-interpolation.png

Bicubic interpolation
Better scaling methods include Lanczos resampling and Mitchell-Netravali filters.
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * 40 by 40 thumbnail of 'Green Sea Shell' fourier interpolated.png
 * Image-after-fourier saturated.png
 * Image-after-fourier saturated.png

Fourier-based interpolation
Simple Fourier based interpolation based on padding of the frequency domain with zero components (a smooth-window-based approach would reduce the ringing). Beside the good conservation of details, notable is the ringing and the circular bleeding of content from the left border to right border (and way around).
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * [[File:40 by 40 thumbnail of 'Green Sea Shell' (x4 DCCI).png]]
 * [[File:Wiki dcci 2x.png]]
 * [[File:Wiki dcci 2x.png]]

Edge-directed interpolation
Edge-directed interpolation algorithms aim to preserve edges in the image after scaling, unlike other algorithms which can produce staircase artifacts around diagonal lines or curves. Examples of algorithms for this task include New Edge-Directed Interpolation (NEDI), Edge-Guided Image Interpolation (EGGI), Iterative Curvature-Based Interpolation (ICBI), and Directional Cubic Convolution Interpolation (DCCI). A study found that DCCI had the best scores in PSNR and SSIM on a series of test images.
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * 40 by 40 thumbnail of 'Green Sea Shell' (Hq4x).png
 * Image-after-hq2x.png
 * Image-after-hq2x.png

Pixel art scaling algorithms (hqx)
For magnifying computer graphics with low resolution and few colors (usually from 2 to 256 colors), better results will be achieved by pixel art scaling algorithms such as hqx or xbr. These produce sharp edges and maintain high level of detail. Unfortunately due to the standardized size of 218x80 pixels, the "Wiki" image cannot use HQ4x or 4xBRZ to better demonstrate the artifacts they may produce such as row shifting.

The example images use HQ4x and HQ2x respectively.
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * 160_by_160_upscaled_thumbnail_of_'Green_Sea_Shell'_(4xBRZ).png
 * Image_after_scaling_(2xBRZ).png
 * Image_after_scaling_(2xBRZ).png

Pixel art scaling algorithms (xbr)
The xbr family is very useful for creating smooth edges. It will however deform the shape significantly, which in many cases creates a very appealing result. However it will create an effect similar to posterization by grouping together local areas into a single colour. It will also remove small details if in-between larger ones which connect together.

The example images use 4xBRZ and 2xBRZ respectively.
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * [[File:160_by_160_upscaled_thumbnail_of_'Green_Sea_Shell'_(GemCutter_Preserve_Details).png|160 by 160 upscaled thumbnail of 'Green Sea Shell' (GemCutter Preserve Details)]]160_by_160_upscaled_thumbnail_of_'Green_Sea_Shell'_(Smooth_Edges).png
 * Image_after_scaling_(GemCutter_Preserve_Details).png
 * Image_after_scaling_(GemCutter_Preserve_Details).png



Pixel art scaling algorithms (GemCutter)
An adaptable technique which can deliver variable amounts of detail or smoothness. It aims to preserve the shape and coordinates of original details, without blurring those details into neighboring ones. It will avoid blending pixels which directly touch each other, and instead only blend pixels with their diagonal neighbors.

The "Cutter" name comes from its tendency to cut corners of squares and turn them into diamonds, as well as create distinct faces along stair-stepped pixels, i.e. those which exist on along the angles of edges found on a diamond. The "Gem" prefix both refers to the diamond cut, and also many traditional gem cuts which involve cutting corners at a 45-degree angle.

The example images use GemCutter Preserve Details (Top), and GemCutter Smooth Edges (Bottom).
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * 40_by_40_thumbnail_of_%27Green_Sea_Shell%27_inscape-potrace_48colors.png
 * [[File:Image scaling example image - intermediate vector representation after applying inkscape vectorization.svg|Vectorization|218px]]
 * [[File:Image scaling example image - intermediate vector representation after applying inkscape vectorization.svg|Vectorization|218px]]

Image tracing
Vectorization first creates a resolution-independent vector representation of the graphic to be scaled. Then the resolution-independent version is rendered as a raster image at the desired resolution. This technique is used by Adobe Illustrator Live Trace, Inkscape, and several recent papers. Scalable Vector Graphics are well suited to simple geometric images, while photographs do not fare well with vectorization due to their complexity.

''Note that the special characteristics of vectors allow for greater resolution example images. The other algorithms are standardized to a resolution of 160x160 and 218x80 pixels respectively.''
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * Green_Sea_Shell_(EDSR).png
 * Wiki_(waifu2x).png
 * Wiki_(waifu2x).png

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.
 * 160_by_160_thumbnail_of_%27Green_Sea_Shell%27.png
 * Green_Sea_Shell_(ESRGAN).png
 * RealESRGAN-x4plus Time Test Augmentation.png
 * RealESRGAN-x4plus Time Test Augmentation.png

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.
 * }