Filters








412 Hits in 6.1 sec

Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool [article]

Tiange Xiang, Hongliang Yuan, Haozhi Huang, Yujin Shi
<span title="2021-03-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we tackle the problems in Monte Carlo rendering by proposing a two-stage denoiser based on the adaptive sampling strategy.  ...  Monte Carlo path tracer renders noisy image sequences at low sampling counts.  ...  Conclusion In this paper, we proposed a novel two-stage denoising framework for Monte Carlo path tracer with adaptive sampling.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.16115v1">arXiv:2103.16115v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zy3a3xoxsndixf6xnm3cbpedji">fatcat:zy3a3xoxsndixf6xnm3cbpedji</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210410184228/https://arxiv.org/pdf/2103.16115v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/09/91/0991edbfbf332b36ad26e281c306a095258387e8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.16115v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

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
<span title="2019-05-10">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Denoising Monte Carlo rendering is different from natural image denoising since inexpensive by-products (feature buffers) can be extracted in the rendering stage.  ...  However, these feature buffers also contain redundant information, which makes Monte Carlo denoising different from natural image denoising.  ...  Denoising Monte Carlo rendering is different from natural image denoising since inexpensive by-products (feature buffers) can be extracted in the rendering stage.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.03908v1">arXiv:1905.03908v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/65sdtdfmxvdjvkmcroysjh7ali">fatcat:65sdtdfmxvdjvkmcroysjh7ali</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200909041117/https://arxiv.org/pdf/1905.03908v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5c/7b/5c7b114f02a7224fd0c4dec7a6199d61bc857213.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1905.03908v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Removing the Noise in Monte Carlo Rendering with General Image Denoising Algorithms

Nima Khademi Kalantari, Pradeep Sen
<span title="">2013</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/p2lpq6bugfcqxk44anrm6yki4m" style="color: black;">Computer graphics forum (Print)</a> </i> &nbsp;
to denoise Monte Carlo rendering.  ...  We show that our framework runs in a few seconds with modern denoising algorithms and produces results that outperform state-of-the-art techniques in Monte Carlo rendering.  ...  gratefully acknowledge the sources of the scenes in the paper: CHESS -Wojciech Jarosz, POOLBALL -Toshiya Hachisuka, TOASTERS -Andrew Kensler, KILLEROO -headus/Rezard (PBRT2 book), SIBENIK -Marko Dabrovic and  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/cgf.12029">doi:10.1111/cgf.12029</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/34v5ysuafvcg5hw4vbjjnxyzii">fatcat:34v5ysuafvcg5hw4vbjjnxyzii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170922215152/http://www.ece.ucsb.edu/%7Epsen/Papers/EG13_RemovingMCNoiseWithGeneralDenoising.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b5/5a/b55aa06551286d1d3a33de0bc554badb75c33602.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/cgf.12029"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Primary-Space Adaptive Control Variates using Piecewise-Polynomial Approximations [article]

Miguel Crespo, Felix Bernal, Adrian Jarabo, Adolfo Muñoz
<span title="2020-08-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
It combines quadrature and Monte Carlo integration, by using a quadrature-base approximation as a control variate of the signal.  ...  Finally, we show how our technique is extensible to integrands of higher dimensionality, by computing the control variate on Monte Carlo estimates of the high-dimensional signal, and accounting for such  ...  ACKNOWLEDGMENTS We thank Ibón Guillén for comments and discussion throughout the project; Manuel Lagunas for help with figures; all the members of the Graphics & Imaging Lab that helped with proof-reading  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.06722v1">arXiv:2008.06722v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vylcklizxvdk3dhtvku3kysrja">fatcat:vylcklizxvdk3dhtvku3kysrja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200821213245/https://arxiv.org/pdf/2008.06722v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e2/d9/e2d9ffda0b7b6840fd45897f4d068f89ecdda0d3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.06722v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deep Radiance Caching: Convolutional Autoencoders Deeper in Ray Tracing [article]

Giulio Jiang, Bernhard Kainz
<span title="2020-07-30">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Rendering realistic images with global illumination is a computationally demanding task and often requires dedicated hardware for feasible runtime.  ...  DRC employs a denoising neural network with Radiance Caching to support a wide range of material types, without the requirement of offline pre-computation or training for each scene.This offers high performance  ...  Acknowledgements: This work has been kindly supported by Intel R and Nvidia.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.02480v2">arXiv:1910.02480v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tmikya7qdvarvbps736z3usnw4">fatcat:tmikya7qdvarvbps736z3usnw4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200808101231/https://arxiv.org/pdf/1910.02480v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.02480v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deep Dose Plugin Towards Real-time Monte Carlo Dose Calculation Through a Deep Learning based Denoising Algorithm [article]

Ti Bai, Biling Wang, Dan Nguyen, Steve Jiang
<span title="2020-12-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Monte Carlo (MC) simulation is considered the gold standard method for radiotherapy dose calculation.  ...  We used two different acceleration strategies to achieve this goal: 1) we applied voxel unshuffle and voxel shuffle operators to decrease the input and output sizes without any information loss, and 2)  ...  Monte Carlo (MC) simulation is considered the most accurate dose calculation algorithm (Kawrakow 2000 , Nelson et al. 1985 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.14959v2">arXiv:2011.14959v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cpq2pbcnyzgw7lly6tyzyyg4vy">fatcat:cpq2pbcnyzgw7lly6tyzyyg4vy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201228090654/https://arxiv.org/pdf/2011.14959v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bb/47/bb47be6ff028a54e13d20c3e6875a14c4b25fcb2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.14959v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Identification of Unsound Grains in Wheat Using Deep Learning and Terahertz Spectral Imaging Technology

Yuying Jiang, Fei Wang, Hongyi Ge, Guangming Li, Xinyu Chen, Li Li, Ming Lv, Yuan Zhang
<span title="2022-04-29">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/yws6xlpwzjf7llvhkn3wayuvfu" style="color: black;">Agronomy</a> </i> &nbsp;
the images with only denoising and feature extraction.  ...  As validated by the ResNet-50 classification network, the proposed model processes images with an accuracy of 94.8%, and the recognition accuracy is improved by 3.7% and 1.9%, respectively, compared to  ...  [17] used an image denoising algorithm with Gaussian kernel weighted mean filtering and nonlinear contrast transform. They combined Markov chain Monte Carlo (MCMC) with the M-H sampling method.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/agronomy12051093">doi:10.3390/agronomy12051093</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uorec5u3uzegta4fjhrdw5flmi">fatcat:uorec5u3uzegta4fjhrdw5flmi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220502234205/https://mdpi-res.com/d_attachment/agronomy/agronomy-12-01093/article_deploy/agronomy-12-01093.pdf?version=1651248222" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f7/92/f792d054662f047445ce49800eefb7c37de36552.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/agronomy12051093"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Path Tracing Denoising based on SURE Adaptive Sampling and Neural Network

Qiwei Xing, Chunyi Chen
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
INDEX TERMS Adaptive sampling, SURE estimator, MLPs network, path tracing, denoising.  ...  In sampling stage, coarse samples are firstly generated. Then each noise level is estimated with SURE. Additional samples are distributed to the pixels with high noise level.  ...  [4] present a recent survey of denoising techniques for Monte Carlo rendering.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2999891">doi:10.1109/access.2020.2999891</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l3efvetnefbptez3ejknvucvgy">fatcat:l3efvetnefbptez3ejknvucvgy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210429122534/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09108228.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2a/db/2adbe5ae262150e3abd330f2d39a3b5b789c5c04.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2999891"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Photon-Driven Neural Path Guiding [article]

Shilin Zhu, Zexiang Xu, Tiancheng Sun, Alexandr Kuznetsov, Mark Meyer, Henrik Wann Jensen, Hao Su, Ravi Ramamoorthi
<span title="2020-10-05">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Although Monte Carlo path tracing is a simple and effective algorithm to synthesize photo-realistic images, it is often very slow to converge to noise-free results when involving complex global illumination  ...  We leverage photons traced from light sources as the input for sampling density reconstruction, which is highly effective for challenging scenes with strong global illumination.  ...  Graham Chair, two Google Fellowships, an Adobe Fellowship and the UC San Diego Center for Visual Computing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01775v1">arXiv:2010.01775v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dsm7kzdf5fbyziqddby6prdkme">fatcat:dsm7kzdf5fbyziqddby6prdkme</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201007003722/https://arxiv.org/pdf/2010.01775v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01775v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Detection of Peach Disease Image Based on Asymptotic Non-local Means and PCNN-IPELM

Shuangjie Huang, Guoxiong Zhou, Mingfang He, Aibin Chen, Wenzhuo Zhang, Yahui Hu
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
proposed by this paper in the last layer instead of the traditional softmax layer, the update method is improved from two aspects to improve the convergence speed and accuracy of the network effectively  ...  Firstly, the method uses the ANLM image denoising algorithm to reduce the interference of the complex background in the image, then uses the parallel convolution neural network proposed by this paper to  ...  kernels of 5 × 5, which are filled with all zeros to generate 16 feature maps of 128 × 128 as the input of pooling layer S2, S2 uses the largest pooling layer with a sampling window size of 2 × 2 to generate  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3011685">doi:10.1109/access.2020.3011685</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/enqvo5sdlranpcjlfzgmzs7wmm">fatcat:enqvo5sdlranpcjlfzgmzs7wmm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210718002853/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09146868.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e2/2b/e22b1aa80ff97eec354137b03daa07dc57876562.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3011685"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Applications of artificial intelligence in nuclear medicine image generation

Zhibiao Cheng, Junhai Wen, Gang Huang, Jianhua Yan
<span title="">2021</span> <i title="AME Publishing Company"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/loautdcoere2pnt4xwr4hiv3yi" style="color: black;">Quantitative Imaging in Medicine and Surgery</a> </i> &nbsp;
Most AI applications in nuclear medicine imaging have focused on the diagnosis, treatment monitoring, and correlation analyses with pathology or specific gene mutation.  ...  This work provides an overview of the application of AI in image generation for single-photon emission computed tomography (SPECT) and positron emission tomography (PET) either without or with anatomical  ...  Monte Carlo simulation of scattering was used as a training label. Figure 4 , the DCNN and Monte Carlo dosimetry results for 90YPET showed a high degree of consistency.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21037/qims-20-1078">doi:10.21037/qims-20-1078</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34079744">pmid:34079744</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8107336/">pmcid:PMC8107336</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/36vdnuatljbmzayjw3azmrtdee">fatcat:36vdnuatljbmzayjw3azmrtdee</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210501210535/https://qims.amegroups.com/article/viewFile/65456/pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/72/a8/72a8607390b2425c6d07b706882f55298527bdb0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21037/qims-20-1078"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8107336" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Power System Transient Stability Assessment Using Stacked Autoencoder and Voting Ensemble

Petar Sarajcev, Antonijo Kunac, Goran Petrovic, Marin Despalatovic
<span title="2021-05-27">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/a2yvk5xhdnhpxjnk6yd33uudqq" style="color: black;">Energies</a> </i> &nbsp;
A complete ML model is proposed for the TSA analysis, built from a denoising stacked autoencoder and a voting ensemble classifier.  ...  Ensemble consist of pooling predictions from a support vector machine and a random forest. Results from the classifier application on the test case power system are reported and discussed.  ...  This confidence can be determined from a statistical distribution of classifier prediction probabilities that is constructed with a repeated Monte Carlo trials.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/en14113148">doi:10.3390/en14113148</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lcfzupsgybgvrhf4r3fsn2abqm">fatcat:lcfzupsgybgvrhf4r3fsn2abqm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210601215609/https://res.mdpi.com/d_attachment/energies/energies-14-03148/article_deploy/energies-14-03148-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/83/23/83234874f6dfcfb9c2c2c94dfc75f127063bcf1e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/en14113148"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

A machine learning approach for filtering Monte Carlo noise

Nima Khademi Kalantari, Steve Bako, Pradeep Sen
<span title="2015-07-27">2015</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/cqrugwalkvcezgalqorn4fwnuu" style="color: black;">ACM Transactions on Graphics</a> </i> &nbsp;
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  ...  Both of these scenes are path-traced and contain severe noise at 4 samples per pixel (spp).  ...  This work was funded by National Science Foundation CA-REER grants IIS-1342931 and IIS-1321168.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2766977">doi:10.1145/2766977</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dmb53bgc2vblfo74yli643qdwa">fatcat:dmb53bgc2vblfo74yli643qdwa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170421084950/http://www.ece.ucsb.edu/%7Epsen/Papers/SIGGRAPH15_LBF.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7a/2c/7a2c0c6d7098b60aca1937593651d802b2edb398.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2766977"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Residual Learning of Cycle-GAN for Seismic data Denoising

Wenda Li, Jian Wang.
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Through RCGAN, we can realize intelligent seismic data denoising work, which dramatically reduces the manual selection and intervention of denoising parameters.  ...  The experiment tests on synthetic and real data also show the effectiveness and superiority of the proposed method RCGAN compared to the state-of-the-art denoising methods.  ...  Finally, we generated a training set contains nearly 25000 samples through the Monte Carlo strategy [24] , which can eliminate useless seismic data that are almost all zeros and not helpful for our training  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3049479">doi:10.1109/access.2021.3049479</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pafxcriaxfhmnn3rina2zkqfea">fatcat:pafxcriaxfhmnn3rina2zkqfea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428133547/https://ieeexplore.ieee.org/ielx7/6287639/9312710/09316158.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e7/ad/e7ada015a901e1b8edc9a20a6294e26196f7376f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3049479"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Two-Stage Learning to Robust Visual Track via CNNs [chapter]

Dan Hu, Xingshe Zhou, Xiaohao Yu, Zhiqiang Hou
<span title="">2015</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In this paper, we explore applying a two-stage learning CNN as a generic feature extractor offline pretrained with a large auxiliary dataset and then transfer its rich feature hierarchies to the robust  ...  Convolutional Neural Networks (CNN) are an alternative type of deep neural network that can be used to model local correlations and reduce translation variations, which have demonstrated great performance  ...  The authors would like to thank the editors for their time and effort. This research was supported by the National Natural Science Foundation of China (61472391, 61403414)  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-21969-1_44">doi:10.1007/978-3-319-21969-1_44</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/62uey7udbnap7m2zp3f47nqh54">fatcat:62uey7udbnap7m2zp3f47nqh54</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200510063401/https://link.springer.com/content/pdf/10.1007%2F978-3-319-21969-1_44.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/60/73/6073673fbc7d744905982b153370accd1507b935.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-21969-1_44"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 412 results