Image Analogies
Author(s): Aaron Hertzmann, Charles Jacobs, Nuria Oliver, Brian Curless, David H. Salesin.
Proceedings: SIGGRAPH '01: Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pp. 327--340, New York, NY, USA, ACM,
2001.
[BibTeX] [DOI]
Abstract:
This paper describes a new framework for processing images by example, called “image analogies.” The framework involves two stages: a design phase, in which a pair of images, with one image purported to be a “?ltered” version of the other, is presented as “training data”; and an application phase, in which the learned ?lter is applied to some new target image in order to create an “analogous” ?ltered result. Image analogies are based on a simple multiscale autoregression, inspired primarily by recent results in texture synthesis. By choosing different types of source image pairs as input, the framework supports a wide variety of “image ?lter” effects, including traditional image ?lters, such as blurring or embossing; improved texture synthesis, in which some textures are synthesized with higher quality than by previous approaches; super-resolution, in which a higher-resolution image is inferred from a low-resolution source; texture transfer, in which images are “texturized” with some arbitrary source texture; artistic ?lters, in which various drawing and painting styles are synthesized based on scanned real-world examples; and texture-by-numbers, in which realistic scenes, composed of a variety of textures, are created using a simple painting interface.
Performance-Driven Hand-Drawn Animation
Ian Buck, Adam Finkelstein, Charles Jacobs, Allison W. Klein, David H. Salesin, Joshua E. Seims, Richard Szeliski, Kentaro Toyama.
1st International Symposium on Non-Photorealistic Animation and Rendering (NPAR'00), pp. 101--108, Annecy, France, June 05 - 07,
2000. [BibTeX]