Filters








17,916 Hits in 5.6 sec

A machine learning approach for filtering Monte Carlo noise

Nima Khademi Kalantari, Steve Bako, Pradeep Sen
2015 ACM Transactions on Graphics  
Our result with a cross-bilateral filter (4 spp) Our result with a non-local means filter (4 spp) Input Ours GT GT Ours Input Figure 1 : We propose a machine learning approach to filter Monte Carlo rendering  ...  Scene credits: KITCHEN - Abstract The most successful approaches for filtering Monte Carlo noise use feature-based filters (e.g., cross-bilateral and cross non-local means filters) that exploit additional  ...  Acknowledgments We thank Nvidia for the hardware donation of a GeForce GTX TI-TAN. This work was funded by National Science Foundation CA-REER grants IIS-1342931 and IIS-1321168.  ... 
doi:10.1145/2766977 fatcat:dmb53bgc2vblfo74yli643qdwa

Evaluation of Artificial Intelligence-Based Denoising Methods for Global Illumination

Soroor Malekmohammadi Faradounbeh, SeongKi Kim
2021 Journal of Information Processing Systems  
The most successful approach to eliminating or reducing Monte Carlo noise uses a feature-based filter.  ...  In this paper, we compare the recent algorithms for removing Monte Carlo noise in terms of their performance and quality. We also describe their advantages and disadvantages.  ...  Sample-based Monte Carlo denoising (SBMCD) A convolutional network can learn to denoise MC renderings directly from the samples.  ... 
doi:10.3745/jips.02.0162 dblp:journals/jips/FaradounbehK21 fatcat:s4fw6suisncmneiyeovh2kqie4

OBJECT TRACKING BASED ON BAYESIAN MONTE CARLO EMPLOYING PARTICLE GAUSSIAN INFORMATION FILTER

K.Saravanan, P. Hima Bindu
2020 Zenodo  
Bayesian approach is used for state estimation to reduce the signal to noise ratio.  ...  In order to solve the above problems, Bayesian Monte Carlo employing Particle Gaussian Information Filter scheme is proposed for object tracking to increase the accuracy for tracking the object.  ...  Figure. 2 2 Particle Gaussian Filter For Object Tracking Figure. 3 3 Architecture Diagram For Bayesian Monte Carlo Employing Particle Gaussian Information Filter Scheme Bayesian Monte Carlo employing  ... 
doi:10.5281/zenodo.3708741 fatcat:dtswwfgthzeizfr2fmm2hdfy3a

Fast Reconstruction for Monte Carlo Rendering Using Deep Convolutional Networks

Xin Yang, Dawei Wang, Wenbo Hu, Lijing Zhao, Xinglin Piao, Dongsheng Zhou, Qiang Zhang, Baocai Yin, Xiaopeng Wei
2018 IEEE Access  
INDEX TERMS Monte Carlo rendering, denoise, deep learning, HDR normalization.  ...  Denoising the Monte Carlo (MC) rendering images is different from denoising the natural images since low-sampled MC renderings have a higher noise level and there are inexpensive by-products (e.g., feature  ...  ACKNOWLEDGEMENT The authors would like to thank the anonymous reviewers for the insightful and constructive comments.  ... 
doi:10.1109/access.2018.2886005 fatcat:uiv6bgmvpngqxir45izlgj6z4e

Follow the Water: Finding Water, Snow and Clouds on Terrestrial Exoplanets with Photometry and Machine Learning [article]

Dang Pham, Lisa Kaltenegger
2022 arXiv   pre-print
Finally, we perform mock Bayesian analysis with Markov-chain Monte Carlo with five filters identified to derive exact surface compositions to test for retrieval feasibility.  ...  XGBoost, a well-known machine learning algorithm, achieves over 90% balanced accuracy in detecting the existence of snow or clouds for S/N≳ 20, and 70% for liquid seawater for S/N ≳ 30.  ...  Speagle, Samantha Berek and Zifan Lin for helpful discussions and comments.  ... 
arXiv:2203.04201v1 fatcat:cilhqfpvxncavjdo7vv2r3ugby

Machine‐learning‐enhanced tail end prediction of structural response statistics in earthquake engineering

Denny Thaler, Marcus Stoffel, Bernd Markert, Franz Bamer
2021 Earthquake engineering & structural dynamics (Print)  
Thus, in this paper, we develop a machine-learning-enhanced Monte Carlo simulation strategy for nonlinear behaving engineering structures.  ...  K E Y W O R D S earthquake generation, elastoplastic structures, Kanai-Tajimi filter, machine learning, Monte Carlo method, neural networks This is an open access article under the terms of the Creative  ...  The nonlinear Kanai-Tajimi filter is introduced in that section, and the machine learning enhanced Monte Carlo simulation strategy is proposed.  ... 
doi:10.1002/eqe.3432 fatcat:ziv7hon3anhg7ekyhztifkpfcq

Monte Carlo Noise Reduction Algorithm Based on Deep Neural Network in Efficient Indoor Scene Rendering System

Xiwen Chen, Jianfei Shen, Qiangyi Li
2022 Advances in Multimedia  
For this problem, we propose a Monte Carlo noise reduction algorithm based on deep neural networks and apply it to the efficient rendering of an indoor scene.  ...  To reduce the variance, Monte Carlo rendering systems often require extensive sampling, which also causes a lot of time spent trying to render noiseless images.  ...  Recently, deep learning methods have shown great ad- vantages in noise reduction for unbiased Monte Carlo path tracing. e work of Kalantari et al. is the first work using neural networks for Monte Carlo  ... 
doi:10.1155/2022/9169772 fatcat:gzsvr3rfk5fuxggdsmy7jmttga

Introduction to Monte Carlo Methods [chapter]

Adrian Barbu, Song-Chun Zhu
2020 Monte Carlo Methods  
Example 1.8 (Restricted Bolzmann Machines) In deep learning, a Restricted Bolzmann machine (RBM) is a neural network with binary inputs and outputs.  ...  Example 1.5 (Monte Carlo Ray tracing) In computer graphics, Monte Carlo integration is used to implement the ray-tracing algorithm for image rendering.  ... 
doi:10.1007/978-981-13-2971-5_1 fatcat:s6gy6s27ovgajomyxdtgwamgzm

Training Deep Neural Networks to Reconstruct Nanoporous Structures From FIB Tomography Images Using Synthetic Training Data

Trushal Sardhara, Roland C. Aydin, Yong Li, Nicolas Piché, Raynald Gauvin, Christian J. Cyron, Martin Ritter
2022 Frontiers in Materials  
To overcome this problem, we present a novel approach to generate synthetic training data in the form of FIB-SEM images generated by Monte Carlo simulations.  ...  Based on this approach, we compare the performance of different machine learning architectures for segmenting FIB tomography data of nanoporous materials.  ...  We present a novel approach to generate synthetic FIB-SEM images using Monte Carlo (MC) simulations to overcome the lack of training data for deep learning methods.  ... 
doi:10.3389/fmats.2022.837006 fatcat:jc7ymflrkbflnaqrtt7fknexhy

DEMC: A Deep Dual-Encoder Network for Denoising Monte Carlo Rendering [article]

Xin Yang, Wenbo Hu, Dawei Wang, Lijing Zhao, Baocai Yin, Qiang Zhang, Xiaopeng Wei, Hongbo Fu
2019 arXiv   pre-print
In this paper, we present DEMC, a deep Dual-Encoder network to remove Monte Carlo noise efficiently while preserving details.  ...  Most of them are noise-free and can provide sufficient details for image reconstruction.  ...  [19] introduced a machine learning approach to the MC denoising field for the first time, though learning based methods have obtained great success on natural image denoising.  ... 
arXiv:1905.03908v1 fatcat:65sdtdfmxvdjvkmcroysjh7ali

Editorial

N. Bourbakis, Jeffrey Tsai, N. Filipovic
2021 EAI Endorsed Transactions on Bioengineering and Bioinformatics  
Konstantinidis and Brown [4] extended the model in order to incorporate non-Gaussian state noise with A Monte Carlo Markov Chain (MCMC) filtering procedure on a self-organizing state-space model.  ...  Carlo framework.  ...  Konstantinidis and Brown [4] extended the model in order to incorporate non-Gaussian state noise with A Monte Carlo Markov Chain (MCMC) filtering procedure on a self-organizing state-space model.  ... 
doi:10.4108/eai.18-2-2021.168722 fatcat:jucsgr4zkrhdnoiaima6rdp5zm

Unscented Kalman Filter-Aided Long Short-Term Memory Approach for Wind Nowcasting

Junghyun Kim, Kyuman Lee
2021 Aerospace (Basel)  
In this paper, we propose a hybrid framework that combines a machine learning model with Kalman filtering for a wind nowcasting problem in the aviation industry.  ...  model, and (3) perform Monte Carlo simulations to quantify uncertainties arising from the modeling process.  ...  Acknowledgments: We would like to thank Tejas Puranik (Aerospace Systems Design Laboratory, Georgia Institute of Technology) for his feedback on this research.  ... 
doi:10.3390/aerospace8090236 doaj:2c6f9ebfa14b4c7da545db8faaab1366 fatcat:lc2b6lnfmfdoxny56hbutgex2y

O-Net: A Convolutional Neural Network for Quantitative Photoacoustic Image Segmentation and Oximetry [article]

Geoffrey P. Luke, Kevin Hoffer-Hawlik, Austin C. Van Namen, Ruibo Shang
2019 arXiv   pre-print
The network was trained on estimated initial pressure distributions from three-dimensional Monte Carlo simulations of light transport in breast tissue.  ...  Estimation of blood oxygenation with spectroscopic photoacoustic imaging is a promising tool for several biomedical applications.  ...  [9, 10] The previous machine learning approaches, however, did not use Monte Carlo simulations of light transport [11, 12] or only used 2-D Monte Carlo simulates to generate the training data.  ... 
arXiv:1911.01935v1 fatcat:3gumtzyeg5cxla3hrwjstmmp4m

Artificial Intelligence for Monte Carlo Simulation in Medical Physics

David Sarrut, Ane Etxebeste, Enrique Muñoz, Nils Krah, Jean Michel Létang
2021 Frontiers in Physics  
Monte Carlo simulation is a key tool both in academic research labs as well as industrial research and development services.  ...  In this article, we review the recent use of Artificial Intelligence methods for Monte Carlo simulation in medical physics and their main associated challenges.  ...  AUTHOR CONTRIBUTIONS All authors listed have made a substantial, direct, and intellectual contribution to the work and approved it for publication. FUNDING  ... 
doi:10.3389/fphy.2021.738112 fatcat:ctfkm54mc5fchj6cjdl7gf22ru

AN EMERGENCE OF GAME STRATEGY IN MULTIAGENT SYSTEMS

PETER LACKO, VLADIMÍR KVASNIČKA, JIŘÍ POSPÍCHAL
2004 International Journal of Computational Intelligence and Applications  
Its advantage is very high learning rate in terms of training cycles. We have proposed usage of extended Kalman filter for reinforcement learning with TD(0) and Monte Carlo method.  ...  In this thesis we focused on subsymbolic approach to machine game play problem. We worked on two different methods of learning.  ...  Its advantage is very high learning rate in terms of training cycles. We have proposed usage of extended Kalman filter for reinforcement learning with TD(0) and Monte Carlo method.  ... 
doi:10.1142/s1469026804001318 fatcat:isrrivef4jewldzfaluwp32wae
« Previous Showing results 1 — 15 out of 17,916 results