1 / 64

Image-Based Visual Hulls

Image-Based Visual Hulls. Wojciech Matusik Chris Buehler Leonard McMillan Massachusetts Institute of Technology Laboratory for Computer Science. Ramesh Raskar University of North Carolina at Chapel Hill Steven J. Gortler Harvard University. Motivation.

brand
Download Presentation

Image-Based Visual Hulls

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-Based Visual Hulls Wojciech Matusik Chris Buehler Leonard McMillanMassachusetts Institute of TechnologyLaboratory for Computer Science Ramesh Raskar University of North Carolinaat Chapel HillSteven J. GortlerHarvard University

  2. Motivation Real-time acquisition and rendering of dynamic scenes

  3. Previous Work • Virtualized Reality (Rander’97, Kanade’97, Narayanan’98) • Visual Hull (Laurentini’94) • Volume Carving (Potmesil’87, Szeliski’93, Seitz’97) • CSG Rendering (Goldfeather’86, Rappoport’97) • Image-Based Rendering (McMillan’95, Debevec’96, Debevec’98)

  4. Contributions • View-dependent image-based visual hull representation • Efficient algorithm for sampling the visual hull • Efficient algorithm computing visibility • A real-time system

  5. What is a Visual Hull?

  6. background + foreground background foreground - = Why use a Visual Hull? • Can be computed robustly • Can be computed efficiently

  7. Rendering Visual Hulls Reference 2 Reference 1 Desired

  8. Build then Sample Reference 2 Reference 1 Desired

  9. Build then Sample Reference 2 Reference 1 Desired

  10. Build then Sample Reference 2 Reference 1 Desired

  11. Build then Sample Reference 2 Reference 1 Desired

  12. Build then Sample Reference 2 Reference 1 Desired

  13. Sample Directly Reference 2 Reference 1 Desired

  14. Sample Directly Reference 2 Reference 1 Desired

  15. Sample Directly Reference 2 Reference 1 Desired

  16. Sample Directly Reference 2 Reference 1 Desired

  17. Sample Directly Reference 2 Reference 1 Desired

  18. Sample Directly Reference 2 Reference 1 Desired

  19. Sample Directly Reference 2 Reference 1 Desired

  20. Sample Directly Reference 2 Reference 1 Desired

  21. Image-Based Computation Reference 1 Desired Reference 2

  22. Observation • Incremental computation along scanlines Desired Reference

  23. Binning • Sort silhouette edges into bins Epipole

  24. Binning • Sort silhouette edges into bins Epipole

  25. Binning • Sort silhouette edges into bins Bin 1 Epipole

  26. Binning • Sort silhouette edges into bins Bin 1 Bin 2 Epipole

  27. Binning • Sort silhouette edges into bins Bin 1 Bin 2 Epipole Bin 3

  28. Binning • Sort silhouette edges into bins Bin 1 Bin 2 Epipole Bin 3 Bin 4

  29. Binning • Sort silhouette edges into bins Bin 1 Bin 2 Epipole Bin 3 Bin 4 Bin 5

  30. Binning • Sort silhouette edges into bins Bin 1 Bin 2 Epipole Bin 3 Bin 4 Bin 5

  31. Scanning Bin 1 Epipole

  32. Scanning Bin 2 Epipole

  33. Scanning Bin 2 Epipole

  34. Scanning Bin 2 Epipole

  35. Scanning Epipole Bin 4

  36. Scanning Epipole Bin 5

  37. Coarse-to-Fine Sampling

  38. IBVH Results • Approximately constant computation per pixel per camera • Parallelizes • Consistent with input silhouettes

  39. Video of IBVH

  40. Shading Algorithm • A view-dependent strategy

  41. Visibility Algorithm

  42. Visibility in 2D Desired view Reference view

  43. Visibility in 2D Front-most Points Desired view Reference view

  44. Visibility in 2D Visible Desired view Reference view

  45. Visibility in 2D Coverage Mask Desired view Reference view

  46. Visibility in 2D Visible Coverage Mask Desired view Reference view

  47. Visibility in 2D Visible Coverage Mask Desired view Reference view

  48. Visibility in 2D Not Visible Coverage Mask Desired view Reference view

  49. Visibility in 2D Coverage Mask Desired view Reference view

  50. Visibility in 2D Visible Coverage Mask Desired view Reference view

More Related