1 / 26

Computational Photography: Image-based Modeling

Computational Photography: Image-based Modeling. Jinxiang Chai. Outline. Stereo matching - Traditional stereo Volumetric stereo - Visual hull - Voxel coloring. Volumetric stereo. Scene Volume V. Input Images (Calibrated). Goal: Determine occupancy, “color” of points in V.

tala
Download Presentation

Computational Photography: 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. Computational Photography:Image-based Modeling Jinxiang Chai

  2. Outline • Stereo matching • - Traditional stereo • Volumetric stereo • - Visual hull • - Voxel coloring

  3. Volumetric stereo Scene Volume V Input Images (Calibrated) Goal: Determine occupancy, “color” of points in V

  4. Discrete formulation: Voxel Coloring Discretized Scene Volume Input Images (Calibrated) • Goal: Assign RGBA values to voxels in V • photo-consistent with images

  5. True Scene All Scenes (CN3) Photo-Consistent Scenes Complexity and computability Discretized Scene Volume 3 N voxels C colors

  6. Issues • Theoretical Questions • Identify class of all photo-consistent scenes • Practical Questions • How do we compute photo-consistent models?

  7. Voxel coloring solutions • 1. C=2 (shape from silhouettes) • Volume intersection [Baumgart 1974] • For more info: Rapid octree construction from image sequences. R. Szeliski, CVGIP: Image Understanding, 58(1):23-32, July 1993. (this paper is apparently not available online) or • W. Matusik, C. Buehler, R. Raskar, L. McMillan, and S. J. Gortler, Image-Based Visual Hulls, SIGGRAPH 2000 ( pdf 1.6 MB ) • 2. C unconstrained, viewpoint constraints • Voxel coloring algorithm [Seitz & Dyer 97]

  8. background + foreground background foreground - = Why use silhouettes? • Can be computed robustly • Can be computed efficiently

  9. Reconstruction from silhouettes (C = 2) Binary Images How to construct 3D volume?

  10. Reconstruction from silhouettes (C = 2) Binary Images • Approach: • Backproject each silhouette • Intersect backprojected volumes

  11. Volume intersection • Reconstruction Contains the True Scene • But is generally not the same • In the limit (all views) get visual hull • Complement of all lines that don’t intersect S

  12. Voxel algorithm for volume intersection • Color voxel black if on silhouette in every image • for M images, N3 voxels • Don’t have to search 2N3 possible scenes! O( ? ),

  13. Visual Hull Results • Download data and results from http://www-cvr.ai.uiuc.edu/ponce_grp/data/visual_hull/

  14. Properties of volume intersection • Pros • Easy to implement, fast • Accelerated via octrees [Szeliski 1993] or interval techniques [Matusik 2000] • Cons • No concavities • Reconstruction is not photo-consistent • Requires identification of silhouettes

  15. Voxel coloring solutions • 1. C=2 (silhouettes) • Volume intersection [Baumgart 1974] • 2. C unconstrained, viewpoint constraints • Voxel coloring algorithm [Seitz & Dyer 97] • For more info: http://www.cs.washington.edu/homes/seitz/papers/ijcv99.pdf • 3. General Case • Space carving [Kutulakos & Seitz 98]

  16. 1. Choose voxel • Color if consistent • (standard deviation of pixel • colors below threshold) 2. Project and correlate Voxel coloring approach Visibility Problem: in which images is each voxel visible?

  17. Known Scene Unknown Scene • Forward Visibility • - Z-buffer • - Painter’s algorithm • known scene • Inverse Visibility?known images The visibility problem Which points are visible in which images?

  18. Layers Depth ordering: visit occluders first! Scene Traversal Condition: depth order is the same for all input views

  19. Panoramic depth ordering • Cameras oriented in many different directions • Planar depth ordering does not apply

  20. Panoramic depth ordering Layers radiate outwards from cameras

  21. Panoramic layering Layers radiate outwards from cameras

  22. Panoramic layering Layers radiate outwards from cameras

  23. Inward-Looking • cameras above scene • Outward-Looking • cameras inside scene Compatible camera configurations • Depth-Order Constraint • Scene outside convex hull of camera centers

  24. Calibrated image acquisition • Calibrated Turntable • 360° rotation (21 images) Selected Dinosaur Images Selected Flower Images

  25. Voxel coloring results Dinosaur Reconstruction 72 K voxels colored 7.6 M voxels tested 7 min. to compute on a 250MHz SGI Flower Reconstruction 70 K voxels colored 7.6 M voxels tested 7 min. to compute on a 250MHz SGI

  26. Modeling Dynamic Objects • Performance capture for articulated and deformable objects (click here)

More Related