An "image analogy" is a method of creating an image filter automatically from training data. In an image analogy process, the transformation between two images A and A' is "learned". Later, given a different image B, it's "analogy" image B' can be generated based on the learned transformation.

The image analogy method has been used to simulate many types of image filters:

• Toy filters, such as blurring or "embossing."
• Texture
  Texture mapping
  Texture mapping is a method for adding detail, surface texture , or color to a computer-generated graphic or 3D model. Its application to 3D graphics was pioneered by Dr Edwin Catmull in his Ph.D. thesis of 1974.-Texture mapping:...
  
  synthesis from an example texture.
• Super-resolution, inferring a high-resolution image from a low-resolutinon source.
• Texture transfer, in which images are "texturized" with some arbitrary source texture.
• Artistic filters, in which various drawing and painting styles, including oil, pastel, and pen-and-ink rendering, are synthesized based on scanned real-world examples.
• Texture-by-numbers, in which realistic scenes, composed of a variety of textures, are created using a simple "painting" interface.
• Image colorization, where color is automatically added to grayscale images.

External links

• Image Analogies at the New York University Media Research Lab