1 / 14

Feature-Based Image Metamorphosis

Feature-Based Image Metamorphosis. Thaddeus Beier, Shawn Neely ACM SIGGRAPH 92’. 97753003 資碩一 陳界誠. What is Morphing?. Morphing = Warping + Cross-dissolving Generalize image warping with a cross-dissolve between images. Warping: shape transform Distort the first image into second one.

Download Presentation

Feature-Based Image Metamorphosis

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. Feature-Based Image Metamorphosis Thaddeus Beier, Shawn Neely ACM SIGGRAPH 92’ 97753003 資碩一 陳界誠

  2. What is Morphing? • Morphing = Warping + Cross-dissolving • Generalize image warping with a cross-dissolve between images. • Warping: shape transform • Distort the first image into second one. • Cross-dissolving: color transform • First image fade out while second image fade in.

  3. Two way to warp an image • Forward mapping • Scans through the source image pixel by pixel, and copies them to appropriate place in the destination image. • Some pixels is the destination might not be painted. • Reverse mapping • Goes through the destination image pixel by pixel and samples the correct pixel from the source image.

  4. One Pair of Lines Transformation

  5. One Pair of Lines Transformation

  6. One Pair of Lines Transformation

  7. Multiple Pairs of Lines

  8. Multiple Pairs of Lines

  9. Multiple Pairs of Lines

  10. Advantages and Disadvantages • Advantage • It is much more expressive. • Disadvantage • Speed and control • Ghost image: unexpected interpolation image

  11. Michael Jackson • Black or White (1) • Black or White (2)

  12. Process flow Input lines segments Lines interpolation Warping Bilinear lines interpolation Image blending

  13. Bilinear Lines interpolation

  14. Image blending • Blend = (1-t)*Src + t*dst , 0 <= t <= 1 T=1 T=0 T=0.5

More Related