reconstruction ii
play

Reconstruction II Neural Networks in Monte Carlo Rendering Philipp - PowerPoint PPT Presentation

Reconstruction II Neural Networks in Monte Carlo Rendering Philipp Slusallek Karol Myszkowski Gurprit Singh 1 Realistic Image Synthesis SS2018 Previous Lecture 2 Realistic Image Synthesis SS2018 Slide from Kartic Subr 3


  1. Reconstruction II Neural Networks in Monte Carlo Rendering Philipp Slusallek Karol Myszkowski Gurprit Singh � 1 Realistic Image Synthesis SS2018

  2. Previous Lecture � 2 Realistic Image Synthesis SS2018

  3. Slide from Kartic Subr � 3 Realistic Image Synthesis SS2018

  4. Depth of field Slide from Jakko Lehtinen � 4

  5. 1 scanline 
 Slide from Jakko Lehtinen � 5

  6. Lens u Slide from Jakko Lehtinen � 6 Screen x

  7. Visibility: SameSurface The trajectories of 
 samples originating from a single 
 apparent surface never intersect. 
 Slide from Jakko Lehtinen � 7

  8. Hachisuka et al. [2008] � 8 Realistic Image Synthesis SS2018

  9. Hachisuka et al. [2008] � 9 Realistic Image Synthesis SS2018

  10. Sen and Darabi [2012] � 10 Realistic Image Synthesis SS2018

  11. Pixels,Random Params,Features The algorithm computes the statistical dependency of (c-f) on the random parameters in ( b ) Sen and Darabi [2012] � 11 Realistic Image Synthesis SS2018

  12. Gaussian Filtering Paris et al. [2009] � 12 Realistic Image Synthesis SS2018

  13. Bilateral Filtering Paris et al. [2009] � 13 Realistic Image Synthesis SS2018

  14. Bilateral vs Gaussian Filtering Paris et al. [2009] � 14 Realistic Image Synthesis SS2018

  15. À la Carte • Introduction to Multi-Layer perceptrons (Neural Networks) • Machine Learning for Filtering Monte Carlo Noise [Kalantari et al. 2015] � 15 Realistic Image Synthesis SS2018

  16. Motivation Bako et al. [2017] � 16 Realistic Image Synthesis SS2018

  17. History of Neural Networks • In 1943, McCulloch and Pitts created a computational model for neural networks • In 1975, Werbos's back propagation algorithm generally accelerated the training of multi-layer networks. • In 1980s, Recurrent Neural Networks were developed � 17 Realistic Image Synthesis SS2018

  18. Multi-Layer Perceptrons � 18 Realistic Image Synthesis SS2018

  19. Classifiers y j = f ( w j x j + b j ) � 19 Realistic Image Synthesis SS2018

  20. Classifiers y j = f ( w j x j + b j ) � 20 Realistic Image Synthesis SS2018

  21. Complex Classifiers y j = f ( w j x j + b j ) Complex classifier � 21 Realistic Image Synthesis SS2018

  22. Complex Classifiers Complex classifier What features can produce this decision rule ? � 22 Realistic Image Synthesis SS2018

  23. Perceptron Classifier x 1 Classifier x 2 x 3 x 4 x 5 . . . 1 � 23 Realistic Image Synthesis SS2018

  24. Perceptron Classifier w 1 x 1 Classifier x 2 w 2 Output x 3 y = f ( w 1 x 1 + w 2 x 2 + ... + w 0 ) x 4 x 5 . . w 0 . 1 � 24 Realistic Image Synthesis SS2018

  25. Multi-layer Perceptron x 1 1 � 25 Realistic Image Synthesis SS2018

  26. Multi-layer Perceptron f X x 1 f X 1 f X � 26 Realistic Image Synthesis SS2018

  27. Multi-layer Perceptron f X w 11 w 10 x 1 w 21 f X w 20 1 w 31 f X w 30 � 27 Realistic Image Synthesis SS2018

  28. Multi-layer Perceptron f X w 11 w 10 x 1 w 21 f X w 20 1 w 31 f X w 30 + x 1 w 11 w 10 + x 1 w 21 w 20 + x 1 w 31 w 30 � 28 Realistic Image Synthesis SS2018

  29. Multi-layer Perceptron f X w 11 w 10 x 1 w 21 f X w 20 1 w 31 f X w 30 + = f ( ( y 1 x 1 w 11 w 10 ( ( = f + x 1 y 2 w 21 w 20 ( + ( = f x 1 w 31 w 30 y 3 � 29 Realistic Image Synthesis SS2018

  30. Multi-layer Perceptron f X w 11 w 1 w 10 x 1 w 21 w 2 f Output X X w 20 1 w 31 w 3 f X w 30 + = f ( ( y 1 x 1 w 11 w 10 ( ( = f + x 1 y 2 w 21 w 20 ( + ( = f x 1 w 31 w 30 y 3 � 30 Realistic Image Synthesis SS2018

  31. Multi-layer Perceptron Input Hidden layers Output layers features f X w 11 w 1 w 10 x 1 w 21 w 2 f Output X X w 20 1 w 31 w 3 f X w 30 y 1 w 1 + = f ( ( y 2 y 1 x 1 w 11 w 10 w 2 ( ( = f + x 1 y 2 w 21 w 20 y 3 w 3 ( + ( = f x 1 w 31 w 30 y 3 � 31 Realistic Image Synthesis SS2018

  32. Multi-layer Perceptron Input Hidden layers Output layers features f X w 11 "Features" are outputs of perceptrons w 1 w 10 x 1 w 21 w 2 f X Output X w 20 1 w 31 w 3 f X w 30 Perceptrons Matrix of second layer weights Matrix of first layer weights w 1 w 11 w 10 w 2 w 21 w 20 w 3 w 31 w 30 � 32 Realistic Image Synthesis SS2018

  33. Features of MLPs Input features Perceptron: Step function with linear decision boundary � 33 Realistic Image Synthesis SS2018

  34. Features of MLPs 2-layer: These outputs are now input features to the next layer "Features" are now decision boundaries (partitions) Layer 1 All linear combination of those partitions give complex partitions � 34 Realistic Image Synthesis SS2018

  35. Features of MLPs These complex outputs become the features for the new layer Layer 2 Layer 1 � 35 Realistic Image Synthesis SS2018

  36. Features of MLPs Deep Neural Networks Layer 2 Layer 1 � 36 Realistic Image Synthesis SS2018

  37. Computational Graph representation of Neural Networks � 37 Realistic Image Synthesis SS2018

  38. Neural Networks Fully connected layers ReLU W 1 0 x 1 N × N N × 1 � 38 Realistic Image Synthesis SS2018

  39. Neural Networks Fully connected layers ReLU W 1 0 x 1 x 2 N × N N × 1 N × 1 � 39 Realistic Image Synthesis SS2018

  40. Neural Networks Fully connected layers ReLU ReLU W 1 W 2 ... 0 x 1 x 2 N × N N × 1 N × N N × 1 � 40 Realistic Image Synthesis SS2018

  41. Neural Networks data Fully connected layers ReLU ReLU W 1 W 2 ... 0 x 1 x 2 N × N N × 1 N × N N × 1 N represents number of pixels in an image � 41 Realistic Image Synthesis SS2018

  42. Neural Networks Unstructured data Fully connected layers ReLU ReLU W 1 W 2 ... 0 x 1 x 2 Computational ReLU Graph * max � 42 Realistic Image Synthesis SS2018

  43. Neural Networks Unstructured data Fully connected layers ReLU ReLU W 1 W 2 ... 0 x 1 x 2 Computational ReLU ReLU Graph * * ... max max � 43 Realistic Image Synthesis SS2018

  44. Two-layer model R R W 1 W 2 . Fully connected layers ReLU ReLU * * max max What can be a loss function ? � 44 Realistic Image Synthesis SS2018

  45. Two-layer model R R W 1 W 2 . Fully connected layers Reference ReLU ReLU * * max max What can be a loss function ? � 45 Realistic Image Synthesis SS2018

  46. Two-layer model R R W 1 W 2 . Fully connected layers Reference ReLU ReLU * * max max What can be a loss function ? � 46 Realistic Image Synthesis SS2018

  47. Two-layer model R R W 1 W 2 . Fully connected layers Reference ReLU ReLU * * max L2 Loss max What can be a loss function ? � 47 Realistic Image Synthesis SS2018

  48. Two-layer model R R W 1 W 2 . Reference 2 ReLU - - max L2 Loss What can be a loss function ? � 48 Realistic Image Synthesis SS2018

  49. Two-layer model R R W 1 W 2 . Reference 2 ReLU - - max L2 Loss What can be a loss function ? � 49 Realistic Image Synthesis SS2018

  50. Two-layer model: Back propagation Source link � 50 Realistic Image Synthesis SS2018

  51. Two-layer model: Back propagation Gradient Descent Algorithm for back propagation Random initialization Global cost minimum � 51 Realistic Image Synthesis SS2018

  52. Back Propagation Slides courtesy: Stanford Online Course � 52 Realistic Image Synthesis SS2018

  53. Back Propagation Slides courtesy: Stanford Online Course � 53 Realistic Image Synthesis SS2018

  54. Back Propagation Slides courtesy: Stanford Online Course � 54 Realistic Image Synthesis SS2018

  55. Back Propagation Slides courtesy: Stanford Online Course � 55 Realistic Image Synthesis SS2018

  56. Back Propagation Slides courtesy: Stanford Online Course � 56 Realistic Image Synthesis SS2018

  57. Back Propagation Slides courtesy: Stanford Online Course � 57 Realistic Image Synthesis SS2018

  58. Back Propagation Slides courtesy: Stanford Online Course � 58 Realistic Image Synthesis SS2018

  59. Back Propagation Slides courtesy: Stanford Online Course � 59 Realistic Image Synthesis SS2018

  60. Back Propagation Slides courtesy: Stanford Online Course � 60 Realistic Image Synthesis SS2018

  61. Machine Learning for Filtering Monte Carlo Noise Kalantari et al. [SIGGRAPH 2015] � 61 Realistic Image Synthesis SS2018

  62. Reconstruction / Denoising Filter weights , Pixel neighborhood � 62 Realistic Image Synthesis SS2018

  63. Filter weights Filter weights For cross Bilateral filters: Pixel neighborhood � 63 Realistic Image Synthesis SS2018

  64. Filter weights Filter weights For cross Bilateral filters: Pixel neighborhood � 64 Realistic Image Synthesis SS2018

  65. Filter weights Filter weights For cross Bilateral filters: Pixel neighborhood Sen and Darabi [2012] � 65 Realistic Image Synthesis SS2018

  66. Filter weights For cross Bilateral filters: Pixel screen coordinates Mean sample color value Scene features � 66 Realistic Image Synthesis SS2018

  67. Filter weights For cross Bilateral filters: Pixel screen coordinates Mean sample color value What are the optimal parameters ? Scene features � 67 Realistic Image Synthesis SS2018

Recommend


More recommend