國立虎尾科技大學 |

Accelerating Approximate Simulation with Deep Learning.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Accelerating Approximate Simulation with Deep Learning./
作者:	Schlachter, Kristofer D.
面頁冊數:	1 online resource (108 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
Contained By:	Dissertation Abstracts International79-08B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780355773354

Accelerating Approximate Simulation with Deep Learning.
Schlachter, Kristofer D.

Accelerating Approximate Simulation with Deep Learning. - 1 online resource (108 pages)

Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.

Thesis (Ph.D.)--New York University, 2018.

Includes bibliographical references

Once a simulation resorts to an approximate numerical solution one is faced with various tradeoffs in accuracy versus computation time. We propose that another approximate solution can be learned for two chosen simulations, which in our case, are just as useful but can be made faster to compute. The two problems addressed in this thesis are fluid simulation and the simulation of diffuse inter-reflection in computer graphics.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355773354Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Accelerating Approximate Simulation with Deep Learning.
LDR:04344ntm a2200373Ki 4500 001 919106
005 20181116131020.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780355773354
035 $a (MiAaPQ)AAI10617140
035 $a (MiAaPQ)nyu:13045
035 $a AAI10617140
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Schlachter, Kristofer D. $3 1193600
245 1 0 $a Accelerating Approximate Simulation with Deep Learning.
264 0 $c 2018
300 $a 1 online resource (108 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-08(E), Section: B.
500 $a Adviser: Ken Perlin.
502 $a Thesis (Ph.D.)--New York University, 2018.
504 $a Includes bibliographical references
520 $a Once a simulation resorts to an approximate numerical solution one is faced with various tradeoffs in accuracy versus computation time. We propose that another approximate solution can be learned for two chosen simulations, which in our case, are just as useful but can be made faster to compute. The two problems addressed in this thesis are fluid simulation and the simulation of diffuse inter-reflection in computer graphics.
520 $a Real-time simulation of fluid and smoke is a long standing problem in computer graphics, where state-of-the-art approaches require large compute resources, making real-time applications often impractical. In this work, we propose a data-driven approach that leverages the approximation power of deep learning methods with the precision of standard fluid solvers to obtain both fast and highly realistic simulations. The proposed method solves the incompressible Euler equations following the standard operator splitting method in which a large, often ill-condition linear system must be solved. We propose replacing this system by learning a Convolutional Network (ConvNet) from a training set of simulations using a semi-supervised learning method to minimize long-term velocity divergence.
520 $a ConvNets are amenable to efficient GPU implementations and, unlike exact iterative solvers, have fixed computational complexity and latency. The proposed hybrid approach restricts the learning task to a linear projection without modeling the well understood advection and body forces. We present real-time 2D and 3D simulations of fluids and smoke; the obtained results are realistic and show good generalization properties to unseen geometry.
520 $a The next simulation that we address is the synthesis of images for training convnets. A challenge with training deep learning models is that they commonly require a large corpus of training data and retrieving sufficient real world data may be unachievable. A solution to this problem can be found in the use of synthetic or simulated training data. However, for simulated photographs or renderings, there hasn't been a systematic approach to comparing the relative benefits of different techniques in image synthesis.
520 $a We compare multiple synthesis techniques to one another as well as the real data that they seek to replicate. We also introduce learned synthesis techniques that either train models better than the most realistic graphical methods used by standard rendering packages or else approach their fidelity using far less computation. We accomplish this by learning shading of geometry as well as denoising the results of low sample Monte Carlo image synthesis. Our major contributions are (i) a dataset that allows comparison of real and synthetic versions of the same scene, (ii) an augmented data representation that boosts the stability of learning, and (iii) three different partially differentiable rendering techniques where lighting, denoising and shading are learned. Finally we are able to generate datasets that can outperform full global illumination rendering and approach the performance of training on real data.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a New York University. $b Computer Science. $3 1184382
773 0 $t Dissertation Abstracts International $g 79-08B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10617140 $z click for full text (PQDT)