1 / 75

Image-based modeling

Image-based modeling. Digital Visual Effects, Spring 2008 Yung-Yu Chuang 2008/5/6. with slides by Richard Szeliski, Steve Seitz and Alexei Efros. Announcements. Project #3 is extend to 5/16 Project #2 artifact voting results. Honorable mention (7): 張子捷 游知澔.

trina
Download Presentation

Image-based modeling

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 modeling Digital Visual Effects, Spring 2008 Yung-Yu Chuang 2008/5/6 with slides by Richard Szeliski, Steve Seitz and Alexei Efros

  2. Announcements • Project #3 is extend to 5/16 • Project #2 artifact voting results

  3. Honorable mention (7): 張子捷游知澔

  4. Honorable mention (9): 胡傳牲高紹航

  5. Third place (10): 吳懿倫張哲瀚

  6. Second place (13):賴韻芊 黃柏瑜

  7. First place (24): 游名揚曾照涵

  8. Outline • Models from multiple (sparse) images • Structure from motion • Facade • Models from single images • Tour into pictures • Single view metrology • Other approaches

  9. Models from multiple images(Façade, Debevec et. al. 1996)

  10. Facade • Use a sparse set of images • Calibrated camera (intrinsic only) • Designed specifically for modeling architecture • Use a set of blocks to approximate architecture • Three components: • geometry reconstruction • texture mapping • model refinement

  11. Idea

  12. Idea

  13. Geometric modeling A block is a geometric primitive with a small set of parameters Hierarchical modeling for a scene Rotation and translation could be constrained

  14. Reasons for block modeling • Architectural scenes are well modeled by geometric primitives. • Blocks provide a high level abstraction, easier to manage and add constraints. • No need to infer surfaces from discrete features; blocks essentially provide prior models for architectures. • Hierarchical block modeling effectively reduces the number of parameters for robustness and efficiency.

  15. Reconstruction minimize

  16. Reconstruction

  17. nonlinear w.r.t. camera and model Reconstruction

  18. Results 3 of 12 photographs

  19. Results

  20. Texture mapping

  21. Texture mapping in real world Demo movie Michael Naimark, San Francisco Museum of Modern Art, 1984

  22. Texture mapping

  23. Texture mapping

  24. View-dependent texture mapping

  25. View-dependent texture mapping VDTM model single texture map VDTM

  26. View-dependent texture mapping

  27. Model-based stereo • Use stereo to refine the geometry known camera viewpoints

  28. Stereo scene point image plane optical center

  29. Stereo • Basic Principle: Triangulation • Gives reconstruction as intersection of two rays • Requires • calibration • point correspondence

  30. epipolar line epipolar line epipolar plane Stereo correspondence • Determine Pixel Correspondence • Pairs of points that correspond to same scene point • Epipolar Constraint • Reduces correspondence problem to 1D search along conjugateepipolar lines

  31. Finding correspondences • apply feature matching criterion (e.g., correlation or Lucas-Kanade) at all pixels simultaneously • search only over epipolar lines (much fewer candidate positions)

  32. Image registration (revisited) • How do we determine correspondences? • block matching or SSD (sum squared differences)d is the disparity (horizontal motion) • How big should the neighborhood be?

  33. Neighborhood size • Smaller neighborhood: more details • Larger neighborhood: fewer isolated mistakes w = 3 w = 20

  34. depth map 3D rendering [Szeliski & Kang ‘95] X z x x’ f f baseline C C’ Depth from disparity input image (1 of 2)

  35. Stereo reconstruction pipeline • Steps • Calibrate cameras • Rectify images • Compute disparity • Estimate depth • Camera calibration errors • Poor image resolution • Occlusions • Violations of brightness constancy (specular reflections) • Large motions • Low-contrast image regions • What will cause errors?

  36. warped offset image Model-based stereo key image offset image

  37. Epipolar geometry

  38. Results

  39. Comparisons single texture, flat VDTM, flat VDTM, model- based stereo

  40. Final results Kite photography

  41. Final results

  42. Results

  43. Results

  44. Commercial packages • REALVIZ ImageModeler

  45. The Matrix Cinefex #79, October 1999.

  46. The Matrix • Academy Awards for Scientific and Technical achievement for 2000 To George Borshukov, Kim Libreri and Dan Piponi for the development of a system for image-based rendering allowing choreographed camera movements through computer graphic reconstructed sets. This was used in The Matrix and Mission Impossible II; See The Matrix Disc #2 for more details

  47. Models from single images

  48. vanishing point Vanishing points • Vanishing point • projection of a point at infinity image plane camera center ground plane

More Related