1. Unfolding an Indoor Origami World David Fouhey, Abhinav Gupta, Martial Hebert 1

2. 2

3. 3

4. Local Evidence 4 Hoiem et al. 2005, Saxena et al. 2005, Fouhey et al. 2013, etc.

5. Constraints 5

6. Constraints for Single Image 3D 6 Local Smoothness Low Level, Generic Hoiem et al. 2005, Saxena et al. 2005, 2008, Munoz et al., 2009, etc.

7. Constraints for Single Image 3D 7 Local Smoothness Low Level, Generic Hoiem et al. 2005, Saxena et al. 2005, 2008, Munoz et al., 2009, etc.

8. Constraints for Single Image 3D 8 Low Level, Generic High Level, Physical

9. High Level, Physical Constraints for Single Image 3D 9 Local Smoothness Low Level, Generic Coughlan and Yuille 2000, etc.

10. High Level, Physical Constraints for Single Image 3D 10 Local Smoothness Low Level, Generic Hedau et al. 2009, Del Pero et al., 2011, Wang et al., 2012, Schwing et al. 2012, etc.

11. High Level, Physical Constraints for Single Image 3D 11 Local Smoothness Low Level, Generic Lee et al. 2010, Xiao et al. 2012, Zhao et al. 2013, Schwing et al., 2013, etc.

12. High Level, Physical Constraints for Single Image 3D 12 Low Level, Generic

13. Mid-level in the Past 13 Huffman 71, Clowes 71, Kanade 80, 81 Sugihara 86, Malik 87, etc.

14. Our Mid-Level Constraints 14

15. This Work 15 Input: Single Image Output: Discrete Scene Parse

16. Overview 16 ParameterizationFormulation Experimental Results

17. Overview 17 ParameterizationFormulation Experimental Results

18. Parameterization 18

19. Parameterization 19 vp 1 vp 2 vp 3 VP Estimator from Hedau et al., 2009

20. Parameterization 20 Two VPs give grid cell

21. Encoding Surface Normals 21

22. Encoding Surface Normals 22

23. Encoding Surface Normals 23

24. Encoding Surface Normals 24 x 1,…, x 400 x 401,…, x 800 x 801,…, x 1200

25. Related Parameterizations 25 vp 1 vp 3 x2x2 x1x1 x3x3 x4x4 Hedau et al., 2009; Wang et al. 2010, Schwing et al., 2012, 2013 vp 2

26. Overview 26 ParameterizationFormulation Experimental Results

27. Parameterization 27

28. Formulation 28

29. Unaries 29

30. Unaries 30 Low c Any 3D Evidence High c

31. Unaries 31 … Input3D Primitive Bank Local: Data-Driven 3D Primitives Fouhey, Gupta, Hebert, 2013

32. Unaries 32 Hedau, Hoiem, Forsyth, 2009 Global: Cuboid Fit + Clutter Mask InputPredicted WallsClutter Mask

33. Binaries 33

34. Convex/Concave Constraints 34 Convex (+) Concave (-)

35. Convex/Concave Constraints 35 Detected Concave (-)

36. Convex/Concave Constraints 36 Detected Concave (-)

37. Convex/Concave Constraints 37 Detected Concave (-)

38. Convex/Concave Constraints 38 Detected Concave (-)

39. Convex/Concave Constraints 39 Detected Concave (-)

40. Detecting Convex/Concave 40 Ground-Truth Discontinuities similar to Gupta, Arbelaez, Malik, 2013 3DP from Fouhey, Gupta, Hebert, 2013 Input3D Primitive Bank … Use 3DP to Transfer Discontinuities

41. Smoothness 41

42. Constraints 42

43. Solving the Model 43

44. Overview 44 ParameterizationFormulation Experimental Results

45. Dataset NYU Depth v2: 795 Train, 654 Test 45

46. Qualitative Results 46

47. Qualitative Results 47

48. Qualitative Results 48

49. Qualitative Results 49

50. Surface Connection Graphs 50 ConvexConcave

51. Baseline Primary Baseline: 3D Primitives (3DP) 51 Fouhey, Gupta, Hebert, 2013 OutputInput

52. Quantitative Results 52 Summary Stats (⁰) (Lower Better) % Good Pixels (Higher Better) 11.25⁰22.5⁰30⁰MeanMedian 3DP 35.952.057.8 36.020.549.4 Hedau et al.34.249.354.440.023.554.1 RMSE Lee et al.18.638.649.943.336.354.6 Proposed37.653.358.935.119.248.7

53. Quantitative Results 53

54. Failure Modes Mistaken but Confident Evidence 54

55. Failure Modes 55 Missing High-Level Modeling

56. Conclusions 56 Single Image Parameterization Formulation Discrete Parse

57. Thank You 57