sure based optimization for adaptive sampling and
play

SURE-based Optimization for Adaptive Sampling and Reconstruction - PowerPoint PPT Presentation

Jan 04, 2024 •313 likes •1.13k views

SURE-based Optimization for Adaptive Sampling and Reconstruction Supplementary Materials Tzu-Mao Li Yu-Ting Wu Yung-Yu Chuang National Taiwan University PART I Equal-Time Comparison Compared Methods: Monte Carlo Greedy Error

  1. SURE-based Optimization for Adaptive Sampling and Reconstruction Supplementary Materials Tzu-Mao Li Yu-Ting Wu Yung-Yu Chuang National Taiwan University

  2. PART I Equal-Time Comparison Compared Methods: • Monte Carlo • Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] • Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] • SURE-based Optimization (our approach, using cross bilateral filters)

  3. SPONZA Global Illumination (Path Tracing) Motion Blur 1600 x 1200

  4. SPONZA Equal-time Monte Carlo , 68 spp, 890.5 sec.

  5. SPONZA Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 63.84 spp, 906.2 sec.

  6. SPONZA Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 16 spp, 1676.1 sec.

  7. SPONZA SURE-based Optimization (Our Approach) , 63.24 spp, 896.0 sec.

  8. SPONZA Reference , 8192 spp

  9. TOWN Environment Lighting Area Lighting Motion Blur 800 x 600

  10. TOWN Equal-time Monte Carlo , 82 spp, 59.9 sec.

  11. TOWN Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 51.82 spp, 61.8 sec.

  12. TOWN Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 8 spp, 272.4 sec.

  13. TOWN SURE-based Optimization (Our Approach) , 39.79 spp, 59.6 sec.

  14. TOWN Reference , 4096 spp

  15. SIBENIK Global Illumination (One-Bounce Path Tracing) Depth of Field 1024 x 1024

  16. SIBENIK Equal-time Monte Carlo , 44 spp, 140.0 sec.

  17. SIBENIK Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 39.86 spp, 135.0 sec.

  18. SIBENIK Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 8 spp, 363.0 sec.

  19. SIBENIK SURE-based Optimization (Our Approach) , 26.69 spp, 140 sec.

  20. SIBENIK Reference , 4096 spp

  21. TEAPOT Environment Lighting Glossy Reflection 800 x 800

  22. TEAPOT Equal-time Monte Carlo , 35 spp, 42.0 sec.

  23. TEAPOT Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 23.96 spp, 44.3 sec.

  24. TEAPOT Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 8 spp, 374.4 sec.

  25. TEAPOT SURE-based Optimization (Our Approach) , 8 spp, 40.4 sec.

  26. TEAPOT Reference , 4096 spp

  27. GARGOYLE Global Illumination (One-Bounce Path Tracing) 1024 x 1024

  28. GARGOYLE Equal-time Monte Carlo , 56 spp, 161.7 sec.

  29. GARGOYLE Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 43.92 spp, 167.4 sec.

  30. GARGOYLE Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 8 spp, 608.3 sec.

  31. GARGOYLE SURE-based Optimization (Our Approach) , 30.90 spp, 160.0 sec.

  32. GARGOYLE Reference , 4096 spp

  33. SANMIGUEL Global Illumination (Path Tracing) 1580 x 986

  34. SANMIGUEL Equal-time Monte Carlo , 70 spp, 1209.4 sec.

  35. SANMIGUEL Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 63.59 spp, 1239.9 sec.

  36. SANMIGUEL Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 16 spp, 2617.9 sec.

  37. SANMIGUEL SURE-based Optimization (Our Approach) , 61.69 spp, 1228.9 sec.

  38. SANMIGUEL Reference , 8192 spp

  39. PART II Equal-Sample Comparison Compared Methods: • Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] • Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] • SURE-based Optimization (our approach, using cross bilateral filters)

  40. SPONZA Global Illumination (Path Tracing) Motion Blur 1600 x 1200

  41. SPONZA Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 16 spp, 210.0 sec.

  42. SPONZA Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 16 spp, 1676.1 sec.

  43. SPONZA SURE-based Optimization (Our Approach) , 16 spp, 273.3 sec.

  44. SPONZA Reference , 8192 spp

  45. TOWN Environment Lighting Area Lighting Motion Blur 800 x 600

  46. TOWN Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 8 spp, 9.4 sec.

  47. TOWN Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 8 spp, 272.4 sec.

  48. TOWN SURE-based Optimization (Our Approach) , 8 spp, 20.0 sec.

  49. TOWN Reference , 4096 spp

  50. SIBENIK Global Illumination (One-Bounce Path Tracing) Depth of Field 1024 x 1024

  51. SIBENIK Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 8 spp, 27.6 sec.

  52. SIBENIK Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 8 spp, 363.0 sec.

  53. SIBENIK SURE-based Optimization (Our Approach) , 8 spp, 64.2 sec.

  54. SIBENIK Reference , 4096 spp

  55. TEAPOT Environment Lighting Glossy Reflection 800 x 800

  56. TEAPOT Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 8 spp, 14.1 sec.

  57. TEAPOT Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 8 spp, 374.4 sec.

  58. TEAPOT SURE-based Optimization (Our Approach) , 8 spp, 40.4 sec.

  59. TEAPOT Reference , 4096 spp

  60. GARGOYLE Global Illumination (One-Bounce Path Tracing) 1024 x 1024

  61. GARGOYLE Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 8 spp, 28.6 sec.

  62. GARGOYLE Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 8 spp, 608.3 sec.

  63. GARGOYLE SURE-based Optimization (Our Approach) , 8 spp, 68.3 sec.

  64. GARGOYLE Reference , 4096 spp

  65. SANMIGUEL Global Illumination (Path Tracing) 1580 x 986

  66. SANMIGUEL Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] , 16 spp, 304.4 sec.

  67. SANMIGUEL Random Parameter Filtering [Sen and Darabi, ACMTOG 2012] , 16 spp, 2617.9 sec.

  68. SANMIGUEL SURE-based Optimization (Our Approach) , 16 spp, 336.3 sec.

  69. SANMIGUEL Reference , 8192 spp

  70. PART III Equal-Time Comparison for Isotropic Gaussian Filters Compared Methods: • Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011] • SURE-based Optimization (our approach, using isotropic Gaussian filters)

  71. TOASTERS Area Lighting Depth of Field 1024 x 1024

  72. TOASTERS Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011]

  73. TOASTERS SURE-based Optimization (Our Approach) , using Isotropic Gaussian Filters

  74. TOASTERS Reference , 4096 spp

  75. TOASTERS – Scale Selection Map Greedy Error Minimization [Rousselle et al., SIGGRAPH Asia 2011]

  76. TOASTERS - Scale Selection Map SURE-based Optimization (Our Approach) , using Isotropic Gaussian Filters

  77. PART IV Equal-Time Comparison for Cross Non-local Means Filters Compared Methods: • Global cross non-local means filters • SURE-based Optimization (our approach, using cross non-local means filters)

  78. TOWN Environment Lighting Area Lighting Motion Blur 800 x 600

  79. TOWN Global Non-local Means Filter , 41.2 spp

  80. TOWN SURE-based Optimization (Our Approach) , using Cross Non-local Means Filters , 41.2 spp, 244.7 sec.

  81. TOWN Reference , 4096 spp

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

AdaGeo: Adaptive Geometric Learning for Optimization and Sampling Gabriele Abbati 1 , Alessandra

AdaGeo: Adaptive Geometric Learning for Optimization and Sampling Gabriele Abbati 1 , Alessandra

AdaGeo: Adaptive Geometric Learning for Opti- mization and Sampling AdaGeo: Adaptive Geometric Learning for Optimization and Sampling Gabriele Abbati 1 , Alessandra Tosi 2 , Seth Flaxman 3 , Michael A Osborne 1 1 University of Oxford, 2

598 views • 30 slides
Adaptive Sampling Strategies for Stochastic Optimization Raghu (Vijaya Raghavendra) Bollapragada 1

Adaptive Sampling Strategies for Stochastic Optimization Raghu (Vijaya Raghavendra) Bollapragada 1

Adaptive Sampling Strategies for Stochastic Optimization Raghu (Vijaya Raghavendra) Bollapragada 1 Richard Byrd 2 Jorge Nocedal 1 1 Northwestern University 2 University of Colorado Boulder January 8, 2018 11 th US - Mexico Workshop on Optimization

1.38k views • 113 slides
ADAPTIVE TWO-STAGE INTEGRATORS FOR SAMPLING ALGORITHMS BASED ON HAMILTONIAN DYNAMICS E.

ADAPTIVE TWO-STAGE INTEGRATORS FOR SAMPLING ALGORITHMS BASED ON HAMILTONIAN DYNAMICS E.

ADAPTIVE TWO-STAGE INTEGRATORS FOR SAMPLING ALGORITHMS BASED ON HAMILTONIAN DYNAMICS E. Akhmatskaya a,c , M. Fernndez-Pends a , T. Radivojevi a , J. M. Sanz-Serna b a Basque Center for Applied Mathematics (BCAM), Bilbao, Spain b Departamento

594 views • 37 slides
Monte Carlo methods for sampling-based Stochastic Optimization Gersende FORT LTCI CNRS &

Monte Carlo methods for sampling-based Stochastic Optimization Gersende FORT LTCI CNRS &

Monte Carlo methods for sampling-based Stochastic Optimization Monte Carlo methods for sampling-based Stochastic Optimization Gersende FORT LTCI CNRS & Telecom ParisTech Paris, France Joint works with B. Jourdain, T. Leli` evre, G.

608 views • 36 slides
SAMPLING-BASED QUERY RE- OPTIMIZATION Wentao Wu Microsoft Research Background 2 Query

SAMPLING-BASED QUERY RE- OPTIMIZATION Wentao Wu Microsoft Research Background 2 Query

1 SAMPLING-BASED QUERY RE- OPTIMIZATION Wentao Wu Microsoft Research Background 2 Query optimization remains challenging despite of decades of efforts and progresses. Cardinality estimation is the key challenge. Selectivity of

400 views • 28 slides
Model-based adaptive spatial sampling for occurrence map construction N. Peyrard and R. Sabbadin

Model-based adaptive spatial sampling for occurrence map construction N. Peyrard and R. Sabbadin

Model-based adaptive spatial sampling for occurrence map construction N. Peyrard and R. Sabbadin CompSust09 - Cornell University - june 2009 p. 1 Mapping spatial processes in environmental management Mapping pest occurrence

834 views • 46 slides
Convergence and Efficiency of Adaptive Importance Sampling techniques with partial biasing

Convergence and Efficiency of Adaptive Importance Sampling techniques with partial biasing

Convergence and Efficiency of Adaptive Importance Sampling techniques with partial biasing Gersende Fort Institut de Math ematiques de Toulouse CNRS France Joint work with B. Jourdain, T. Leli` evre and G. Stoltz Talk based on the paper

260 views • 21 slides
Optimization of a Sampling Plan using R Optimization of a Sampling Plan using R for Economic Data

Optimization of a Sampling Plan using R Optimization of a Sampling Plan using R for Economic Data

UseR Conference 2009 Agrocampus Rennes Optimization of a Sampling Plan using R Optimization of a Sampling Plan using R for Economic Data Collection for Economic Data Collection Application to the Atlantic French Fleet Application to the

442 views • 18 slides
Multi-Armed Bandits: Non-adaptive and Adaptive Sampling Instructor: Sham Kakade 1 The

Multi-Armed Bandits: Non-adaptive and Adaptive Sampling Instructor: Sham Kakade 1 The

CSE 547/Stat 548: Machine Learning for Big Data Lecture Multi-Armed Bandits: Non-adaptive and Adaptive Sampling Instructor: Sham Kakade 1 The (stochastic) multi-armed bandit problem The basic paradigm is as follows: K Independent Arms: a

273 views • 5 slides
Adaptive Environment Sampling on CPU and GPU Asen Atanasov Vladimir Koylazov Blagovest Taskov

Adaptive Environment Sampling on CPU and GPU Asen Atanasov Vladimir Koylazov Blagovest Taskov

Adaptive Environment Sampling on CPU and GPU Asen Atanasov Vladimir Koylazov Blagovest Taskov Jaroslav Kivnek Alexander Soklev Vassillen Chizhov Image-based lighting (IBL) HDR images courtesy of NoEmotion IBL noise Portals Existing

774 views • 35 slides
Accelerating PDE-Constrained Optimization Problems using Adaptive Reduced-Order Models Matthew J.

Accelerating PDE-Constrained Optimization Problems using Adaptive Reduced-Order Models Matthew J.

Introduction Optimization via Adaptive Model Reduction Large-Scale, Constrained Optimization Conclusion Accelerating PDE-Constrained Optimization Problems using Adaptive Reduced-Order Models Matthew J. Zahr Advisor: Charbel Farhat

1.08k views • 90 slides
Accelerating PDE-Constrained Optimization Problems using Adaptive Reduced-Order Models Matthew J.

Accelerating PDE-Constrained Optimization Problems using Adaptive Reduced-Order Models Matthew J.

Introduction Optimization via Adaptive Model Reduction Large-Scale, Constrained Optimization Conclusion Accelerating PDE-Constrained Optimization Problems using Adaptive Reduced-Order Models Matthew J. Zahr Advisor: Charbel Farhat

1.24k views • 85 slides
Adaptive Sampling for Sensor Networks Seminarvortrag von Philippe Bourquin Betreuung: Silvia

Adaptive Sampling for Sensor Networks Seminarvortrag von Philippe Bourquin Betreuung: Silvia

Adaptive Sampling for Sensor Networks Seminarvortrag von Philippe Bourquin Betreuung: Silvia Santini Overview Sensor Networks: an Introduction 1. Problems / Requirements in SNs 2. Adaptive Sampling 3. Example 1: Feedback Control

189 views • 8 slides
Sampling Lecture 30 ME EN 575 Andrew Ning aning@byu.edu Outline Surrogate Based Optimization

Sampling Lecture 30 ME EN 575 Andrew Ning aning@byu.edu Outline Surrogate Based Optimization

Sampling Lecture 30 ME EN 575 Andrew Ning aning@byu.edu Outline Surrogate Based Optimization (SBO) Introduction Sampling Surrogate Based Optimization (SBO) Introduction What is a surrogate model? When might one use a surrogate model?

362 views • 9 slides
A Nonlinear Trust-Region Framework for PDE-Constrained Optimization Using Adaptive Model

A Nonlinear Trust-Region Framework for PDE-Constrained Optimization Using Adaptive Model

Introduction Optimization via Adaptive Model Reduction Large-Scale, Constrained Optimization Conclusion A Nonlinear Trust-Region Framework for PDE-Constrained Optimization Using Adaptive Model Reduction Matthew J. Zahr Institute for

336 views • 33 slides
Recent Advances in Adaptive Sampling and Reconstruction for Monte

Recent Advances in Adaptive Sampling and Reconstruction for Monte

Recent Advances in Adaptive Sampling and Reconstruction for Monte Carlo Rendering M. Zwicker W. Jarosz J. Lehtinen B. Moon R. Ramamoorthi Univ. of Bern Disney Research Aalto

543 views • 13 slides
Nation Matrimonial l Real Property Law In Information Ses ession Ang ngeli lina Amaral,

Nation Matrimonial l Real Property Law In Information Ses ession Ang ngeli lina Amaral,

Pictou Landing First Nation Matrimonial l Real Property Law In Information Ses ession Ang ngeli lina Amaral, Mikmaw Lawyer Gia iancarla la Fr Fran ancis is, Mikmaw Lawy wyer Mar arch 6, , 2017 The Confederacy of Mainland

347 views • 34 slides
Retail in Russia The Initial Questions November 2013 Murat Gursey COO Atrium Russia Print:

Retail in Russia The Initial Questions November 2013 Murat Gursey COO Atrium Russia Print:

Retail in Russia The Initial Questions November 2013 Murat Gursey COO Atrium Russia Print: December 5, 2013 - 09:42 Atrium Snapshot Owner, Manager and Developer of supermarket anchored shopping centers Leading owner, operator and

328 views • 14 slides
OSK Holdings Bhd 29 th Annual General Meeting Financials 31 December 2018 30 April 2019

OSK Holdings Bhd 29 th Annual General Meeting Financials 31 December 2018 30 April 2019

OSK Holdings Bhd 29 th Annual General Meeting Financials 31 December 2018 30 April 2019 Disclaimer This presentation/document (presentation) has been prepared by OSK Holdings Berhad and its subsidiaries (OSK Group) . All

571 views • 32 slides
Cera Sanitaryware Limited Corporate Presentation Style. Innovation. Leadership March 2019

Cera Sanitaryware Limited Corporate Presentation Style. Innovation. Leadership March 2019

Cera Sanitaryware Limited Corporate Presentation Style. Innovation. Leadership March 2019 Disclaimer This presentation and the accompanying slides (the Presentation), which have been prepared by Cera Sanitaryware Limited company, have

461 views • 24 slides
Forge.mil Open Source Collaborative Principles Within the DoD Guy Martin, Aaron Lippold -

Forge.mil Open Source Collaborative Principles Within the DoD Guy Martin, Aaron Lippold -

Forge.mil Open Source Collaborative Principles Within the DoD Guy Martin, Aaron Lippold - Forge.mil Community Management Team community@forge.mil Twitter: @ForgeMil Twitter Tag: #forgemil Setting Expectations Will Cover: A case study for

403 views • 12 slides
International Student Services Presents: Graduate Advisor Workshop Presenter: Amanda Brinlee

International Student Services Presents: Graduate Advisor Workshop Presenter: Amanda Brinlee

International Student Services Presents: Graduate Advisor Workshop Presenter: Amanda Brinlee Senior International Student Advisor We will discuss: International Students Health Insurance ISSIS and other IT projects Academic Process and

485 views • 12 slides
Ecosystem Workgroup Climate & Communities Initiative September 2018 Agenda Item G.3.

Ecosystem Workgroup Climate & Communities Initiative September 2018 Agenda Item G.3.

Agenda Item G.3.b Supplemental Presentation 1 September 2018 Ecosystem Workgroup Climate & Communities Initiative September 2018 Agenda Item G.3. November 17, 2019 1 2 The goal of a cross-FMP Climate and Communities Initiative is to

313 views • 15 slides
AAHC Services 01 Affordable Housing Properties 16 properties in the City of Ann Arbor 412

AAHC Services 01 Affordable Housing Properties 16 properties in the City of Ann Arbor 412

AAHC Services 01 Affordable Housing Properties 16 properties in the City of Ann Arbor 412 apartments 02 Voucher Programs 2,073 Vouchers 03 Family Self-Sufficiency & Homeownership Programs 99 130 FSS participants 10 Homeowners 04

337 views • 33 slides

More recommend