1 / 15

Image Quilting and Apples

Image Quilting and Apples. By Zach Broderick A presentation of the paper “Image Quilting for Texture Synthesis and Transfer” by Alexei A. Efros and William T. Freeman. Texture Synthesis. (Images taken from paper). Infinitely Large Output. Sample of Texture. Output texture is:

hafwen
Télécharger la présentation

Image Quilting and Apples

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Image Quilting and Apples By Zach Broderick A presentation of the paper “Image Quilting for Texture Synthesis and Transfer” by Alexei A. Efros and William T. Freeman

  2. Texture Synthesis (Images taken from paper)

  3. Infinitely Large Output Sample of Texture • Output texture is: • Same resolution • Non-repeating • Seamless • Must be perceived as “same”

  4. Previous Methods • Tiling (bad seams, repetitive) • Stochastic (doesn’t work for structured) • Pixel-based (SLOW, poor for structured) • Random Patches/Blending (poor seams)

  5. Image Quilting • Copy patches (like the random patch method) based on neighborhood (like pixel method) • Faster (predetermined pixels/less search space), maintains structure of regular textures • Seams smoothed with graph cut through least error path (Image from Wikipedia)

  6. Image Quilting (Diagram from paper)

  7. An In-Depth Look at the Image Quilting Algorithm: Overview • Copy tiles from the source image to the destination image in a left to right, top to bottom fashion, with an overlap of about 1/6 the tile size on the top and left regions. • In selecting each of these tiles, search the source image space S for the tile with the least mean squared error in the overlap region (the first tile can be selected at random). • When copying each tile, calculate the minimum error path cut in each of the overlap regions, and only copy the portion of the tile within the cut.

  8. Error Calculation

  9. Path Cut

  10. Path Cut Cont’d…

  11. Texture Transfer • Algorithm can be generalized to provide texture transfer capabilities (image from paper)

  12. Problems • Repetition often occurs (see raspberries) • Occasional glaring seams (mutant tomatoes)

  13. Demonstration

  14. Questions?

More Related