1 / 56

Computational Photography and Video: Time-Lapse Video Analysis & Editing

Computational Photography and Video: Time-Lapse Video Analysis & Editing. Prof. Marc Pollefeys Dr. Gabriel Brostow. Last Time. Today’s schedule. Factored Time-Lapse Video Sunkavalli, Matusik, Pfister, Rusinkiewicz, Siggraph 2007 Computational Time-Lapse Video

dwhitehouse
Download Presentation

Computational Photography and Video: Time-Lapse Video Analysis & Editing

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. Computational Photography and Video: Time-Lapse VideoAnalysis & Editing Prof. Marc Pollefeys Dr. Gabriel Brostow

  2. Last Time

  3. Today’s schedule • Factored Time-Lapse Video • Sunkavalli, Matusik, Pfister, Rusinkiewicz, Siggraph 2007 • Computational Time-Lapse Video • Bennett & McMillan, Siggraph 2007 • Video Synopsis & Indexing, • Pritch, Rav-Acha, Peleg, ICCV 2007

  4. Time-lapse Photography • Definition: when frames are captured at a lower rate than the rate at which they will ultimately be played back. • Compare to • Slow-motion • Bullet-time

  5. Examples

  6. Time-lapse Filmmaker’s Challenges

  7. Time-lapse Filmmaker’s Challenges • Lighting changes (strobing) • High frequency motion (missed action) • Saturation & exposure • Camera motion: intentional or not • Triggering / data storage / camera safety • Useful? Editable?

  8. Factored Time-Lapse Video Sunkavalli, Matusik, Pfister, Rusinkiewicz SIGGRAPH 2007 Project web page

  9. Remember Intrinsic Images from Video? • Weiss ICCV’01

  10. Outdoors: More Than Just Color vs Illumination? Original No Shadows Given: Daytime, under clear-sky conditions

  11. Outdoors: More Than Just Color vs Illumination? Wishlist Remove shadows Render new shadows Change albedo Change global illumination Original No Shadows Given: Daytime, under clear-sky conditions

  12. Outdoors: More Than Just Color vs Illumination? Original No Shadows Lighting due to sun? sky? Surface Normals?

  13. Formulation • size: width x height x time • F: xyt volume of frames over time • Isky: Accumulated intensity due to sky-light • Isun: Accumulated intensity due to sun-light • Ssun: Binary; is a pixel in shadow

  14. Intuition

  15. Separate Sky first • Photoshop! • Just to pick “non-surfaces” • When is sun’s contribution == 0? • Leaving just sky’s contribution

  16. “Definitely” shadow: median of darkest 20%, then threshold at 1.5x

  17. Bilateral Filter “Definitely” Shadow

  18. How Did Skylight Change? • Isky: Accumulated intensity due to sky-light • Wsky: Sky-light image • Hsky: Sky-light basis curve (1D function!!) • Whole scene got brighter/darker together

  19. Blue: skylight curve (same one)

  20. Factorization • Decompose appearance into • per-pixel W • H curve • Alternating Constrained Least Squares (ACLS): • H(t) is held fixed while W is optimized using least squares, then vice versa

  21. ACLS: Alternating Constrained Least Squares • Inverse shade trees for non-parametric material representation and editing, • Lawrence et al., Siggraph 2006, code online

  22. Original and Isky

  23. Isky and Reconstruction

  24. Explained Sky…

  25. Now Decompose Sun’s Contributions • Isun: Accumulated intensity due to sun-light • Wsun: Sun-light image, per-pixel weights • Hsun: Sun-light basis curve • : Shift-map; per pixel offset in time

  26. Isun: Accumulated intensity due to sun-light • Wsun: Sun-light image, per-pixel weights • Hsun: Sun-light basis curve • : Shift-map; per pixel offset in time

  27. Isun: Accumulated intensity due to sun-light • Wsun: Sun-light image, per-pixel weights • Hsun: Sun-light basis curve • : Shift-map; per pixel offset in time

  28. Total sunlight contribution Sunlight image (like on moon) Shift map Sunlight

  29. Factorize Again! • For each image, subtract off Isky(t) • Ssun: Sky-light mask, serves as C, confidence map • ACLS again • But add 3rd update phase, searching for that minimizes reconstruction error of scaled + offset H(t) vs. F(t)

  30. Green: sunlight curve (same one, but time-shifted)

  31. Isun(t) Wsun

  32. Reconstruction

  33. Does It Work?

  34. Video: FactoredTimeLapseV

  35. What have we gained? • Can • Remove shadows • Change albedo • Change amount of global illumination • Compression • Render new shadows: • We have 1 component of the per-pixel Normals, N

  36. Estimated Normals (1D)

  37. Recap: Manipulating Normals

  38. Does the old definition of time-lapse still hold?

  39. Today’s schedule • Factored Time-Lapse Video • Sunkavalli, Matusik, Pfister, Rusinkiewicz, Siggraph 2007 • Computational Time-Lapse Video • Bennett & McMillan, Siggraph 2007 • Video Synopsis & Indexing, • Pritch, Rav-Acha, Peleg, ICCV 2007 Still 1 frame at a time Examine parts of frames

  40. (Quick Overview of)Computational Time-Lapse Video Bennett & McMillan Siggraph 2007 (Project web page)

  41. Sampling in 1D • Uniform • Interpolate linearly+ piece-wise • Same # of samples, but where needed! • Optimum polygonal approximation of digitized curves, Perez & Vidal, PRL’94 • Use dynamic programming to find global min.

  42. Completely User-controllable:Min-Change, Min-Error, Median, etc

  43. Video

More Related