input
play

Input Rectified stereo image pair All correspondences lie in - PowerPoint PPT Presentation

Problem Definition 3 Input Rectified stereo image pair All correspondences lie in same scan lines Output Disparity map of the reference view Foreground: large disparity Background: small disparity Matching Cost


  1. Problem Definition 3 Input • Rectified stereo image pair • All correspondences lie in same scan lines Output • Disparity map of the reference view • Foreground: large disparity • Background: small disparity

  2. Matching Cost Volume 2 𝐷 𝑦, 𝑧, 𝑒 denotes the matching cost of pixel (x,y) at different disparity level d

  3. WTA (Winner Takes All) 3 • 𝐷 𝑦, 𝑧, 𝑒 denotes the matching cost of pixel (x,y) at different disparity level d • Select d with lowest cost as final disparity

  4. Some Milestone Approaches 4 • Graph Cut (Energy Minimization via Graph Cuts) Boykov et al., ICCV 1999 • ASW (Cost Aggregation by adaptive support weight) Yoon and Kweon, CVPR 2005 • SGM (Semi-Global Matching) Hirschmuller, CVPR 2005, PAMI 2008 • PatchMatch Stereo (Cost aggregation using slanted support windows) Bleyer et al., BMVC 2011

  5. Graph Cut 5 • Frame the problem as an energy minimization on a multi- labeled MRF • Solve the MRF by Graph Cut Unary Cost • Photo consistency of each label Pairwise Cost • Penalize disparity difference between neighboring pixels

  6. Graph Cut 6 • Frame the problem as an energy minimization on a multi- labeled MRF • Solve the MRF by Graph Cut

  7. Traditional Local Methods 7 𝐷 𝑦, 𝑧, 𝑒 Cost aggregation Bilateral filter each 𝐷(𝑦, 𝑧, 𝑗) 𝐷 𝐵 𝑦, 𝑧, 𝑒

  8. ASW (Adaptive Support Weights) 8 • Given an initial matching cost volume, • Refine the volume by aggregating cost locally and adaptively

  9. ASW (Adaptive Support Weights) 9 • Given an initial matching cost volume, • Refine the volume by aggregating cost locally and adaptively

  10. SGM (Semi-Global Matching) 10 • Instead of aggregating cost at a local window, • SGM Aggregate cost in paths

  11. SGM (Semi-Global Matching) 11 • Instead of aggregating cost at a local window, • SGM Aggregate cost in paths

  12. PatchMatch Stereo 12 • Parametrize each pixel as a disparity plane • Aggregate cost in the slanted window induced by the plane • Too many (infinite) possible states, solve by PatchMatch

  13. PatchMatch Stereo 13 • Parametrize each pixel as a disparity plane • Aggregate cost in the slanted window induced by the plane • Too many (infinite) possible states, solve by PatchMatch

  14. MeshStereo: A Global Stereo Model with Mesh Alignment Regularization for View Interpolation Chi Zhang, Zhiwei Li, Yanhua Cheng, Rui Cai, Hongyang Chao, Yong Rui Presented by Chi Zhang Dec. 15 th , 2015

  15. Motivation 2 Goal • Output high-quality mesh for view interpolation Motivation • Depth estimation and mesh generation are separated in traditional approach, which is not optimal in terms of rendering • We aim at unifying such separation, and develop an integrated stereo approach for view interpolation

  16. Movitation 3 Traditional Pipeline • I L , I R -> Point Clouds (Disparity Maps) • Point Clouds -> Mesh • Mesh -> New View Angles Ours • I L , I R -> Mesh • Mesh -> New View Angles

  17. Formulation 17 Mesh Representation • Delauney triangulated SLIC Segmentation • Assign a depth value to each vertex • Lifting the 2D triangulation to 3D naturally generate a mesh Technical Difficulty • How to split vertices into multiple copies at depth discontinuities Solution • Assign a splitting probability to each vertex

  18. Formulation 18 Parameterization A Splitting probability for each 2D vertex denoted by α A depth value for each triangle’s barycenter and a normal for each triangle denoted by N , D

  19. Formulation 19 Objective Function • Objective function is a two-layered MRF glued by an Alignment energy term Lower Layer MRF Gluer Upper Layer MRF

  20. Formulation 20 The Lower Layer • The lower layer MRF is on the “dual” grid of the 2D triangulation

  21. Formulation 21 The Lower Layer • Favorites photo-consistent triangles

  22. Formulation 22 The Lower Layer • Encourages normal smoothness. Encouraged Discouraged

  23. Formulation 23 The Upper Layer • The upper layer MRF is on the original grid of the 2D triangulation

  24. Formulation 24 The Upper Layer • Favorite non-split vertices on homogeneous regions

  25. Formulation 25 Similar visual complexity Similar visual complexity Similar visual complexity The Upper Layer • Encourages similar splitting properties when adjacent vertices share similar “visual complexity” Non-similar visual complexity

  26. Formulation 26 The Upper Layer • Encourages similar splitting properties when adjacent vertices share similar “visual complexity”

  27. Formulation 27 The Gluer • Enforce strong alignment or split a 2D vertex to multiple copies in 3D according to corresponding splitting probability

  28. Optimization 28 Objective Function Optimization • Iterative Gradient Descent in the blue part and the orange part • Fix N , D , minimize the orange part w.r.t. α in closed form • Fix α , minimize the blue part by PatchMatch with iterative relaxation ( detail at next page )

  29. Optimization 29 The orange part sub-energy Optimization • Fix α , minimize E LOWER by PatchMatch with iterative relaxation • When 𝜄 goes to ∞ , minimizing E RELAXED is equivalent to minizing E LOWER

  30. Optimization 30 The orange part sub-energy Optimization • Fix α , minimize E LOWER by PatchMatch with iterative relaxation Minimize by PatchMatch Minimize in closed form

  31. Results 31 Stereo Results on Herodion Dataset

  32. Results 32 Ranking on Midd3 benchmark

  33. Results 33 Examples of generated meshes

  34. Results 34 Some synthesized views

  35. Results 35 Some synthesized views

  36. Conclusion 18 • We proposed an integrated stereo model for view interpolation • Take I L , I R as inputs, produce a mesh directly • It achieves state-of-the-arts performance on both stereo quality and rendering

  37. Thank you! The End

Recommend


More recommend