radiance predicting neural networks
play

Radiance-Predicting Neural Networks SIMON KALLWEIT, Disney Research - PowerPoint PPT Presentation

Jan 04, 2023 β€’686 likes β€’911 views

Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks SIMON KALLWEIT, Disney Research and ETH Zrich et al. ACM Transactions on Graphics, Publication date: November 2017 Presenter: MinKu Kang In Previous Talk

  1. Deep Scattering: Rendering Atmospheric Clouds with Radiance-Predicting Neural Networks SIMON KALLWEIT, Disney Research and ETH ZΓΌrich et al. ACM Transactions on Graphics, Publication date: November 2017 Presenter: MinKu Kang

  2. In Previous Talk from Dennis Ambient sound propagation

  3. Cloud Rendering edge-darkening effects silverlining https://www.youtube.com/watch?v=0MJl9IF_3fI

  4. Scattering of Light Light scattering in microscale , not just in macro scale http://ww2010.atmos.uiuc.edu/(Gh)/guides/mtr/opt/mch/sct.rxml

  5. Problem Configuration & Notation πœ•: π‘’π‘—π‘ π‘“π‘‘π‘’π‘—π‘π‘œ 𝑦: π‘šπ‘π‘‘π‘π‘’π‘—π‘π‘œ We want to know (compute) the radiance at ( 𝑦 , πœ• ) To render a whole cloud image, We need to know the radiance at all (visible) positions and directions Problem : How to efficiently compute the radiance at a specific position and a direction ?

  6. Problem Configuration & Notation πœ•: π‘’π‘—π‘ π‘“π‘‘π‘’π‘—π‘π‘œ 𝑦: π‘šπ‘π‘‘π‘π‘’π‘—π‘π‘œ We want to know (compute) the radiance at ( 𝑦 , πœ• ) To render a whole cloud image, We need to know the radiance at all (visible) positions and directions But , there are too many discrete particles to consider Problem : How to efficiently compute the (they are not even polygons!). Is this possible to use rendering equation we have radiance at a specific position and a direction ? learned ?

  7. Radiative Transfer The radiative transfer equation Integrating both sides of the differential RTE along Ο‰ : extinction coefficient

  8. Radiative Transfer Boundary π‘‘π‘π‘œπ‘’π‘ π‘—π‘π‘£π‘’π‘—π‘π‘œ 𝑔𝑏𝑑𝑒𝑝𝑠: πœ• βˆ™ ෝ πœ• πœ• ෝ Neighborhood πœ• surface 𝑇 2 𝑦

  9. RADIANCE-PREDICTING NEURAL NETWORKS The in-scattered radiance Rule out uncollided radiance (directly from the sun) This is what the NN predicts (estimate)

  10. A combination of Monte Carlo integration and neural networks Monte-Carlo Integration The in-scattered radiance This is what the NN predicts (estimate)

  11. RADIANCE-PREDICTING NEURAL NETWORKS Want to find (learn) a function Such that, given S : shading configuration around 𝑦, πœ• it predicts

  12. RADIANCE-PREDICTING NEURAL NETWORKS Want to find (learn) a function via using

  13. The Descriptor at a specific configuration ( 𝑦, πœ• ) Each descriptor consists of 5 Γ— 5 Γ— 9 stencils β€’ β€’ The stencil is oriented towards the light source The stencil at level k is scaled by 2 π‘™βˆ’1 β€’ β€’ Two levels of the hierarchy are shown here β€’ They use K=10 levels (10 stenciles) β€’ Each stencil is formed by 225 points

  14. The Descriptor at a specific configuration ( 𝑦, πœ• ) 𝑦: π‘šπ‘π‘‘π‘π‘’π‘—π‘π‘œ πœ•: π‘’π‘—π‘ π‘“π‘‘π‘’π‘—π‘π‘œ πœ• π‘š : π‘’π‘—π‘ π‘“π‘‘π‘’π‘—π‘π‘œ 𝑒𝑝π‘₯𝑏𝑠𝑒𝑑 π‘’β„Žπ‘“ π‘šπ‘—π‘•β„Žπ‘’ 𝑑𝑝𝑣𝑠𝑑𝑓 The Descriptor:

  15. Neural Network Architecture (progressive feeding) The most finest scale stencil The most coarse scale Outout (L)

  16. Training Configuration Ground Truth data from Path Tracing N = ~15 million samples Adam update rule using the default learning rate The minibatches of size |B| = 1000 It requires ∼ 12 h of training on a single GPU

  17. Result (Test Time) Path Tracing Radiance-Predicting Neural Networks (RPNN)

  18. Result (Test Time) They argued that RPNN (seconds to minutes.) converges 24 times faster than PT

  19. Experiment - Neural Network Architecture Validation error Progressive feeding The entire stencil hierarchy is input to the first layer This highlights the benefit of the progressive feeding that provides means to better adapt to signals at different frequency scales.

  20. Experiment – Stencil Size Validation error A good balance between accuracy and the cost of querying the density values and number of trainable parameters in the network

  21. Summary Radiative Transfer Equation (RTE) Progressive Feeding Neural Network Hierarchical Stencil Descriptor

Recommend

Predicting Temporal Sets with Deep Neural Networks Le Yu, Leilei Sun*, Bowen Du, Chuanren Liu, Hui

Predicting Temporal Sets with Deep Neural Networks Le Yu, Leilei Sun*, Bowen Du, Chuanren Liu, Hui

Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 20), August 23 27, 2020, Virtual Event, CA, USA. Predicting Temporal Sets with Deep Neural Networks Le Yu, Leilei Sun*, Bowen Du, Chuanren Liu, Hui

440 views β€’ 18 slides
Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions Jimmy Lei Ba,

Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions Jimmy Lei Ba,

Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions Jimmy Lei Ba, Kevin Swersky, Sanja Fidler, Ruslan Salakhutdinov ICCV 2015 Presenter: Fartash Faghri Zero-shot Learning Classify images of an unseen class

156 views β€’ 12 slides
DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks

DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks Fabien Geyer 1,2 and Steffen Bondorf 3 INFOCOM 2019 Wednesday 1 st May, 2019 1 Chair of Network Architectures and Services 3 Dept. of Information

711 views β€’ 57 slides
Outline Evolution of neurocomputing Artificial neural networks Feed forward

Outline Evolution of neurocomputing Artificial neural networks Feed forward

Introduction to Neural Networks and Deep Learning Ling Guan References: S. Haykin, Neural Networks , 2 nd Edition, New Jersey: Prentice Hall, 1. 2004. C. M. Bishop, Neural Networks for Pattern Re cognition, New York: 2. Oxford University

451 views β€’ 17 slides
Neural Networks for Predicting Algorithm Runtime Distributions Katharina Eggensperger, Marius

Neural Networks for Predicting Algorithm Runtime Distributions Katharina Eggensperger, Marius

Neural Networks for Predicting Algorithm Runtime Distributions Katharina Eggensperger, Marius Lindauer & Frank Hutter Paper ID #2772 Eggensperger, Lindauer and Hutter DistNet: Runtime Distribution Prediction #2772 IJCAI2018 Motivation

588 views β€’ 27 slides
Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

1.17k views β€’ 91 slides
Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

852 views β€’ 33 slides
CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks

CONVOLUTIONAL AND RECURRENT NEURAL NETWORKS Neural networks Fully connected networks Neuron Non-linearity Softmax layer DNN training Loss function and regularization SGD and backprop Learning rate Overfitting

1.8k views β€’ 86 slides
Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2019 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they

1.57k views β€’ 124 slides
Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural

Neural Networks 1. Introduction Spring 2020 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they

1.63k views β€’ 119 slides
Relaxation and Hopfield Networks Neural Networks Neural Networks - Hopfield 1 Bibliography

Relaxation and Hopfield Networks Neural Networks Neural Networks - Hopfield 1 Bibliography

Relaxation and Hopfield Networks Neural Networks Neural Networks - Hopfield 1 Bibliography Hopfield, J. J., "Neural networks and physical systems with emergent collective computational abilities," Proceedings of the National Academy

367 views β€’ 19 slides
Neural Networks and their Application to Go Neural Networks Learning Blackjack Theory Training

Neural Networks and their Application to Go Neural Networks Learning Blackjack Theory Training

Neural Networks and their Application to Go A. Bausch Neural Networks and their Application to Go Neural Networks Learning Blackjack Theory Training neural networks Problems AlphaGo Anne-Marie Bausch The Game of Go Policy Network

280 views β€’ 24 slides
(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning

(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning

(Very) Brief Introduction to Neural Networks IITP-03 Algorithms for NLP 1 / 31 Learning objectives What are neural networks? What are deep neural networks? How do we train neural networks? What variants of neural network

331 views β€’ 31 slides
How Neural Networks (NN) Biological Neuron: A . . . Can (Hopefully) Learn Artificial Neural . .

How Neural Networks (NN) Biological Neuron: A . . . Can (Hopefully) Learn Artificial Neural . .

Need for Machine . . . Neural Networks . . . How to Speed Up . . . Neural Networks: A . . . How Neural Networks (NN) Biological Neuron: A . . . Can (Hopefully) Learn Artificial Neural . . . Resulting Algorithm Faster by Taking Into How to

464 views β€’ 17 slides
Outline Why model neural networks? Modeling Neural Networks A brief look at the neuron.

Outline Why model neural networks? Modeling Neural Networks A brief look at the neuron.

Outline Why model neural networks? Modeling Neural Networks A brief look at the neuron. A look at some current works. Adding an evolutionary strategy. Paul Nuytten CPSC 607 Why Model Neural Networks? The Neuron The nervous

697 views β€’ 4 slides
Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking

Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking

Introduction to Deep Neural Networks 0. Logistics Spring 2020 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In

987 views β€’ 40 slides
Propagating Error Backward Hyperparameters for Neural Networks } Multi-layer (deep) neural

Propagating Error Backward Hyperparameters for Neural Networks } Multi-layer (deep) neural

Learning in Neural Networks w 1,3 w 3,5 1 3 5 w w 1,4 3,6 w w 2,3 4,5 2 4 6 w w 2,4 4,6 Class #18: Back-Propagation; } A neural network can learn a classification function by Tuning Hyper-Parameters adjusting its weights to

259 views β€’ 4 slides
Neural Networks Hugo Larochelle ( @hugo_larochelle ) Google Brain 2 NEURAL NETWORKS What

Neural Networks Hugo Larochelle ( @hugo_larochelle ) Google Brain 2 NEURAL NETWORKS What

Neural Networks Hugo Larochelle ( @hugo_larochelle ) Google Brain 2 NEURAL NETWORKS What well cover ... f ( x ) computer vision architectures - convolutional networks - data augmentation 1 - residual networks ... ...

1.29k views β€’ 75 slides
Neural Networks Oskar Taubert (SCC) SCC 1 15.01.2020 Oskar Taubert - Neural Networks SCC

Neural Networks Oskar Taubert (SCC) SCC 1 15.01.2020 Oskar Taubert - Neural Networks SCC

Neural Networks Oskar Taubert (SCC) SCC 1 15.01.2020 Oskar Taubert - Neural Networks SCC www.kit.edu KIT The Research University in the Helmholtz Association Neural Network Concept (very) remotely brain inspired computational system

479 views β€’ 25 slides
Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova

Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova

Introduction to Artificial Intelligence Neural Networks - Deep Learning for NLP Janyl Jumadinova November 21, 2016 Neural Networks 2/20 Neural Networks 3/20 Neural Networks Neural computing requires a number of neurons , to be connected

813 views β€’ 21 slides
7. Artificial neural networks Introduction to neural networks Despite struggling to understand

7. Artificial neural networks Introduction to neural networks Despite struggling to understand

7. Artificial neural networks Introduction to neural networks Despite struggling to understand intricacies of protein, cell, and network function within the brain, neuroscientists would agree on the following simplistic description of how the

157 views β€’ 11 slides
Predicting Surgery Duration w. Neural Heteroscedastic Regression Nathan Ng, Rodney Gabriel,

Predicting Surgery Duration w. Neural Heteroscedastic Regression Nathan Ng, Rodney Gabriel,

Predicting Surgery Duration w. Neural Heteroscedastic Regression Nathan Ng, Rodney Gabriel, Charles Elkan, Julian McAuley, Zachary Lipton https://arxiv.org/abs/1702.05386 Predicting Surgery Duration Surgeries are expensive, partly due to

465 views β€’ 10 slides
Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons

Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons

Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons Multilayer networks Applications of neural networks Chapter 20 2 Brains 10 11 neurons of > 20 types, 10 14 synapses, 1ms10ms cycle

804 views β€’ 47 slides
Modeling Neural Networks Paul Nuytten CPSC 607 Outline Why model neural networks? A

Modeling Neural Networks Paul Nuytten CPSC 607 Outline Why model neural networks? A

Modeling Neural Networks Paul Nuytten CPSC 607 Outline Why model neural networks? A brief look at the neuron. A look at some current works. Adding an evolutionary strategy. Why Model Neural Networks? The nervous system is a

1.22k views β€’ 23 slides

More recommend