1 / 50

CS448f: Image Processing For Photography and Vision

CS448f: Image Processing For Photography and Vision. Blending and Pyramids. Blending. We’ve aligned our images. What now? Averaging Weighted averaging min/max/median. Noise reduction by Averaging. 2 Shots. 4 Shots. 8 Shots. 16 Shots. Noise Reduction by Averaging.

vangie
Télécharger la présentation

CS448f: Image Processing For Photography and Vision

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. CS448f: Image Processing For Photography and Vision Blending and Pyramids

  2. Blending • We’ve aligned our images. What now? • Averaging • Weighted averaging • min/max/median

  3. Noise reduction by Averaging

  4. 2 Shots

  5. 4 Shots

  6. 8 Shots

  7. 16 Shots

  8. Noise Reduction by Averaging • We’re averaging random variables X and Y • Both have variance S2 • Variance of X+Y = 2S2 • Std.Dev. of X+Y = sqrt(2) . S • Std.Dev of (X+Y)/2 = sqrt(2)/2 . S • Ie, every time we take twice as many photos, we reduce noise by sqrt(2)

  9. Noise Reduction by Averaging • Average 4 photos: noise gets reduced 2x • Average 8 photos: noise gets reduced 3x • Average 16 photos: noise gets reduced 4x

  10. Noise Reduction by Median • (demo)

  11. Median v Average

  12. Median v Average

  13. Can we identify the bad pixels? • They’re unlike their neighbours • Instead of averaging, weighted average • where weight = similarity to neighbours

  14. Weighted Average

  15. Can we identify the bad pixels? • They’re unlike their neighbours • Instead of averaging, weighted average • where weight = similarity to neighbours • Favors blurriness 

  16. Input

  17. Other uses of Median • Removing Transient Occluders • (live demo) • (Gates demo) • (surf demo)

  18. Panorama Stitching

  19. Panorama Stitching

  20. Panorama Stitching

  21. Panorama Stitching

  22. Panorama Stitching

  23. Multiple Exposure Fusion

  24. Multiple Exposure Fusion

  25. Multiple Exposure Fusion

  26. Multiple Exposure Fusion

  27. Multiple Exposure Fusion

  28. Multiple Exposure Fusion

  29. Multiple Exposure Fusion

  30. Multiple Exposure Fusion

  31. Multiple Exposure Fusion

  32. Multiple Exposure Fusion

  33. Multiple Exposure Fusion

  34. Focus Fusion

  35. Focus Fusion

  36. Focus Fusion

  37. Focus Fusion

  38. Focus Fusion

  39. Pyramids • We’ve been breaking images into two terms for a variety of apps • Coarse + Fine • More generally we can break it into many terms: • Very coarse + finer + finer ... + finest.

  40. Pyramids • We can do this by blurring more and more:

  41. Pyramids • And then (optionally) taking differences - -

  42. Pyramids • The coarse layers can be stored at low res. Gaussian Pyramid Laplacian Pyramid

  43. Pyramids • How much memory does this use?

  44. Pyramid Uses: • Sampling arbitrarily sized Gaussians • Equalizing an image • The different levels represent different frequency ranges • We can scale each frequency level and recombine • Blending multiple images

  45. Pyramid Blending • Key Insight: • Coarse structure should blend very slowly between images (lots of feathering), while fine details should transition more quickly. • More robust to tricky cases than plain old compositing

  46. Inputs:

  47. Compositing: Hard Mask

  48. Compositing: Soft Mask

  49. Multi-Band Blending

  50. Exposure Fusion • http://research.edm.uhasselt.be/~tmertens/papers/exposure_fusion_reduced.pdf

More Related