1 / 33

Fast Normal Map Acquisition Using an LCD Screen Emitting Gradient Patterns

Fast Normal Map Acquisition Using an LCD Screen Emitting Gradient Patterns Yannick Francken, Chris Hermans , Tom Cuypers , Philippe Bekaert Hasselt University - tUL - IBBT Expertise Centre for Digital Media Belgium { firstname.lastname }@ uhasselt.be. Goal.

rob
Download Presentation

Fast Normal Map Acquisition Using an LCD Screen Emitting Gradient Patterns

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. Fast Normal Map Acquisition Using an LCD Screen Emitting Gradient Patterns Yannick Francken, Chris Hermans, Tom Cuypers, Philippe Bekaert Hasselt University - tUL - IBBT Expertise Centre for Digital Media Belgium {firstname.lastname}@uhasselt.be

  2. Goal Acquire normal maps of diffuse surfaces Diffuse Object Normal Map

  3. Related Work Typically expensive / complex / specialized setups [Wang & Dana,PAMI06] [Ma et al., EGSR07] [Paterson et al. Eurographics05] [Malzbenderet al., SIGGRAPH01]

  4. Related Work … COMBINE

  5. Setup Real

  6. Setup Schematic Camera + Polarizing filter LCD Screen Diffuse Object

  7. Display4 Patterns

  8. Display4 Patterns

  9. Display4 Patterns

  10. Display4 Patterns

  11. Overview INPUT OUTPUT

  12. Pattern Definitions

  13. Derivation albedo light normal Lambertian reflection

  14. Derivation capture intensity Lambertian reflection pattern set of lights

  15. Derivation Example constant constant

  16. Overview Example constant constant constant constant constant constant

  17. Practical Calibration Geometric Color Captured Emitted [Bouguet, 06] [Franckenet al., CRV07]

  18. Practical Remove Specularities specular + diffuse diffuse specular polarizing filter rotated 0˚ polarizing filter rotated 90˚

  19. Results Photograph Normal map Synthesized view

  20. Results Photograph Normal map Synthesized view

  21. Results Photograph Normal map Synthesized view

  22. Limits  Sufficient albedo required

  23. Limits Sufficient albedo required Ignores inter-reflections

  24. Limits Sufficient albedo required Ignores inter-reflections Large objects

  25. Limits Sufficient albedo required Ignores inter-reflections Large objects Self shadowing

  26. Conclusion • Efficient • Only 4 input images required

  27. Conclusion • Efficient • Only 4 input images required • Common hardware

  28. Conclusion constant constant constant constant constant constant • Efficient • Only 4 input images required • Common hardware • Easy and efficient implementation

  29. Conclusion • Efficient • Only 4 input images required • Common hardware • Easy and efficient implementation • Pleasing results

  30. Future Work ? • Global approach • Use diffuse andspecularcomponents • Rotate object, align and merge input

  31. Questions? constant constant constant constant constant constant yannick.francken@uhasselt.be http://research.edm.uhasselt.be/~yfrancken • Summary • Efficient: 4 input images • Common hardware • Easy and efficient • Pleasing results

  32. Questions? constant constant constant constant constant constant yannick.francken@uhasselt.be http://research.edm.uhasselt.be/~yfrancken • Summary • Efficient: 4 input images • Common hardware • Easy and efficient • Pleasing results

  33. Depth Map

More Related