Full Text:   <1464>

Summary:  <1266>

CLC number: TP399

On-line Access: 2021-07-20

Received: 2020-04-01

Revision Accepted: 2020-08-07

Crosschecked: 2021-05-07

Cited: 0

Clicked: 3092

Citations:  Bibtex RefMan EndNote GB/T7714

 ORCID:

Tian Feng

https://orcid.org/0000-0001-9691-3266

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2021 Vol.22 No.7 P.915-925

http://doi.org/10.1631/FITEE.2000141


A review of computer graphics approaches to urban modeling from a machine learning perspective


Author(s):  Tian Feng, Feiyi Fan, Tomasz Bednarz

Affiliation(s):  Department of Computer Science and Information Technology, La Trobe University, VIC 3086, Australia; more

Corresponding email(s):   t.feng@latrobe.edu.au

Key Words:  Urban modeling, Computer graphics, Machine learning, Deep learning


Share this article to: More |Next Article >>>

Tian Feng, Feiyi Fan, Tomasz Bednarz. A review of computer graphics approaches to urban modeling from a machine learning perspective[J]. Frontiers of Information Technology & Electronic Engineering, 2021, 22(7): 915-925.

@article{title="A review of computer graphics approaches to urban modeling from a machine learning perspective",
author="Tian Feng, Feiyi Fan, Tomasz Bednarz",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="22",
number="7",
pages="915-925",
year="2021",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2000141"
}

%0 Journal Article
%T A review of computer graphics approaches to urban modeling from a machine learning perspective
%A Tian Feng
%A Feiyi Fan
%A Tomasz Bednarz
%J Frontiers of Information Technology & Electronic Engineering
%V 22
%N 7
%P 915-925
%@ 2095-9184
%D 2021
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2000141

TY - JOUR
T1 - A review of computer graphics approaches to urban modeling from a machine learning perspective
A1 - Tian Feng
A1 - Feiyi Fan
A1 - Tomasz Bednarz
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 22
IS - 7
SP - 915
EP - 925
%@ 2095-9184
Y1 - 2021
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2000141


Abstract: 
urban modeling facilitates the generation of virtual environments for various scenarios about cities. It requires expertise and consideration, and therefore consumes massive time and computation resources. Nevertheless, related tasks sometimes result in dissatisfaction or even failure. These challenges have received significant attention from researchers in the area of computer graphics. Meanwhile, the burgeoning development of artificial intelligence motivates people to exploit machine learning, and hence improves the conventional solutions. In this paper, we present a review of approaches to urban modeling in computer graphics using machine learning in the literature published between 2010 and 2019. This serves as an overview of the current state of research on urban modeling from a machine learning perspective.

机器学习视角下的城市建模计算机图形方法综述

冯天1,范非易2,Tomasz BEDNARZ3,4
1乐卓博大学计算机科学与信息技术系,澳大利亚维多利亚州,3086
2中国科学院计算技术研究所,中国北京市,100190
3新南威尔士大学扩展感知与交互中心,澳大利亚新南威尔士州,2021
4联邦科学与工业研究组织Data61,澳大利亚新南威尔士州,2015
摘要:城市建模为生成城市不同场景下的虚拟环境提供了便利。城市建模需要专业知识和考虑,并消耗大量时间和计算资源。即便如此,与之相关的任务有时仍以不满意的结果甚至失败告终。这些挑战得到了计算机图形学领域学者的大量关注。同时,人工智能的蓬勃发展激励人们充分利用机器学习以改进现有解决方案。本文回顾了2010至2019年间发表的文献,对计算机图形领域中使用机器学习的城市建模方法进行综述。本文可作为机器学习视角下城市建模研究现状的概述。

关键词:城市建模;计算机图形学;机器学习;深度学习

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Affara L, Nan LL, Ghanem B, et al., 2016. Large scale asset extraction for urban images. Proc 14th European Conf on Computer Vision, p.437-452.

[2]Aleotti F, Zaccaroni G, Bartolomei L, et al., 2020. Real-time single image depth perception in the wild with handheld devices. https://arxiv.org/abs/2006.05724

[3]AlHalawani S, Yang YL, Liu H, et al., 2013. Interactive facades analysis and synthesis of semi-regular facades. Comput Graph Forum, 32(2pt2):215-224.

[4]Aliaga DG, 2012. 3D design and modeling of smart cities from a computer graphics perspective. Int Schol Res Notic, 2012:728913.

[5]Bao F, Schwarz M, Wonka P, 2013a. Procedural facade variations from a single layout. ACM Trans Graph, 32(1):8:1-8:13.

[6]Bao F, Yan DM, Mitra NJ, et al., 2013b. Generating and exploring good building layouts. ACM Trans Graph, 32(4):122:1-122:10.

[7]Beneš J, Wilkie A, Křivánek J, 2014. Procedural modelling of urban road networks. Comput Graph Forum, 33(6):132-142.

[8]Besuievsky G, Patow G, 2013. Customizable LOD for procedural architecture. Comput Graph Forum, 32(8):26-34.

[9]Bishop CM, 2006. Pattern Recognition and Machine Learning. Springer, New York, USA.

[10]Caruana R, Niculescu-Mizil A, 2006. An empirical comparison of supervised learning algorithms. Proc 23rd Int Conf on Machine Learning, p.161-168.

[11]Ceylan D, Mitra NJ, Li H, et al., 2012. Factored facade acquisition using symmetric line arrangements. Comput Graph Forum, 31(2pt3):671-680.

[12]Ceylan D, Mitra NJ, Zheng Y, et al., 2014. Coupled structure-from-motion and 3D symmetry detection for urban facades. ACM Trans Graph, 33(1):2.

[13]Cortes C, Vapnik V, 1995. Support-vector networks. Mach Learn, 20(3):273-297.

[14]Cover T, Hart P, 1967. Nearest neighbor pattern classification. IEEE Trans Inform Theory, 13(1):21-27.

[15]Dang M, Ceylan D, Neubert B, et al., 2014. Safe: structure-aware facade editing. Comput Graph Forum, 33(2):83-93.

[16]Dang M, Lienhard S, Ceylan D, et al., 2015. Interactive design of probability density functions for shape grammars. ACM Trans Graph, 34(6):206.

[17]Demir I, Aliaga DG, Benes B, 2014. Proceduralization of buildings at city scale. Proc 2nd Int Conf on 3D Vision, p.456-463.

[18]Emilien A, Bernhardt A, Peytavie A, et al., 2012. Procedural generation of villages on arbitrary terrains. Vis Comput, 28(6-8):809-818.

[19]Feng T, Yu LF, Yeung SK, et al., 2016. Crowd-driven mid-scale layout design. ACM Trans Graph, 35(4):132.

[20]Feng T, Truong QT, Nguyen DT, et al., 2018. Urban zoning using higher-order Markov random fields on multi-view imagery data. Proc 15th European Conf on Computer Vision, p.627-644.

[21]Fernandes GD, Fernandes AR, 2018. Space colonisation for procedural road generation. Proc Int Conf on Graphics and Interaction, p.1-8.

[22]Fukushima K, 1980. Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern, 36(4):193-202.

[23]Galin E, Peytavie A, Maréchal N, et al., 2010. Procedural generation of roads. Comput Graph Forum, 29(2):429-438.

[24]Galin E, Peytavie A, Guérin E, et al., 2011. Authoring hierarchical road networks. Comput Graph Forum, 30(7):2021-2030.

[25]Garcia-Dorado I, Aliaga DG, Ukkusuri SV, 2014. Designing large-scale interactive traffic animations for urban modeling. Comput Graph Forum, 33(2):411-420.

[26]Garcia-Dorado I, Aliaga DG, Bhalachandran S, et al., 2017. Fast weather simulation for inverse procedural design of 3D urban models. ACM Trans Graph, 36(2):21.

[27]Goldblatt R, Stuhlmacher MF, Tellman B, et al., 2018. Using landsat and nighttime lights for supervised pixel-based image classification of urban land cover. Remot Sens Environ, 205:253-275.

[28]Goodfellow I, Bengio Y, Courville A, 2016. Deep Learning. MIT Press, Cambridge, UK.

[29]Goodfellow I, Pouget-Abadie J, Mirza M, et al., 2014. Generative adversarial nets. Proc 27th Int Conf on Neural Information Processing Systems, p.2672-2680.

[30]Guerrero P, Jeschke S, Wimmer M, et al., 2015. Learning shape placements by example. ACM Trans Graph, 34(4):108.

[31]Guo YJ, Chen EX, Guo Y, et al., 2017. Deep highway unit network for land cover type classification with GF-3 SAR imagery. Proc SAR in Big Data Era: Models, Methods and Applications, p.1-6.

[32]Hartmann S, Weinmann M, Wessel R, et al., 2017. StreetGAN: towards road network synthesis with generative adversarial networks. Proc 25th Int Conf in Central Europe on Computer Graphics, Visualization and Computer Vision, p.133-142.

[33]Hassoun MH, 1995. Fundamentals of Artificial Neural Networks. MIT Press, Cambridge, USA.

[34]Hastie T, Tibshirani R, Friedman J, 2009. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, New York, USA.

[35]Ho TK, 1995. Random decision forests. Proc 3rd Int Conf on Document Analysis and Recognition, p.278.

[36]Hopfield JJ, 1982. Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA, 79(8):2554-2558.

[37]Hu YJ, Gao S, Janowicz K, et al., 2015. Extracting and understanding urban areas of interest using geotagged photos. Comput Environ Urban Syst, 54:240-254.

[38]Huang HB, Kalogerakis E, Yumer E, et al., 2017. Shape synthesis from sketches via procedural models and convolutional networks. IEEE Trans Vis Comput Graph, 23(8):2003-2013.

[39]Ilčík M, Musialski P, Auzinger T, et al., 2015. Layer-based procedural design of façades. Comput Graph Forum, 34(2):205-216.

[40]Isola P, Zhu J, Zhou TH, et al., 2016. Image-to-image translation with conditional adversarial networks. https://arxiv.org/abs/1611.07004

[41]James G, Witten D, Hastie T, et al., 2014. An Introduction to Statistical Learning: with Applications in R. Springer, New York, USA.

[42]Kaelbling LP, Littman ML, Moore AW, 1996. Reinforcement learning: a survey. J Artif Intell Res, 4(1):237-285.

[43]Kelly T, Wonka P, Mueller P, 2015. Interactive dimensioning of parametric models. Comput Graph Forum, 34(2):117-129.

[44]Kelly T, Femiani J, Wonka P, et al., 2017. BigSUR: large-scale structured urban reconstruction. ACM Trans Graph, 36(6):204.

[45]Kelly T, Guerrero P, Steed A, et al., 2018. FrankenGAN: guided detail synthesis for building mass models using style-synchonized GANs. ACM Trans Graph, 37(6):216.

[46]Khanum M, Mahboob T, Imtiaz W, et al., 2015. A survey on unsupervised machine learning algorithms for automation, classification and maintenance. Int J Comput Appl, 119(13):34-39.

[47]Kim S, Kim D, Choi S, 2020. CityCraft: 3D virtual city creation from a single image. Vis Comput, 36(5):911-924.

[48]Krecklau L, Pavic D, Kobbelt L, 2010. Generalized use of non-terminal symbols for procedural modeling. Comput Graph Forum, 29(8):2291-2303.

[49]Krizhevsky A, Sutskever I, Hinton GE, 2017. ImageNet classification with deep convolutional neural networks. Commun ACM, 60(6):84-90.

[50]Kuang ZZ, Chan B, Yu YZ, et al., 2013. A compact random-access representation for urban modeling and rendering. ACM Trans Graph, 32(6):172.

[51]Lafarge F, Mallet C, 2011. Building large urban environments from unstructured point data. Proc Int Conf on Computer Vision, p.1068-1075.

[52]Lecun Y, Bottou L, Bengio Y, et al., 1998. Gradient-based learning applied to document recognition. Proc IEEE, 86(11):2278-2324.

[53]Li HN, Jia YH, Zhou Y, 2018. Urban expansion pattern analysis and planning implementation evaluation based on using fully convolution neural network to extract land range. NeuroQuantology, 16(5):814-822.

[54]Li ML, Wonka P, Nan LL, 2016. Manhattan-world urban reconstruction from point clouds. Proc 14th European Conf on Computer Vision, p.54-69.

[55]Lienhard S, Lau C, Müller P, et al., 2017. Design transformations for rule-based procedural modeling. Comput Graph Forum, 36(2):39-48.

[56]Lin H, Gao JZ, Zhou Y, et al., 2013. Semantic decomposition and reconstruction of residential scenes from LiDAR data. ACM Trans Graph, 32(4):66.

[57]Lindenmayer A, 1968. Mathematical models for cellular interactions in development I. Filaments with one-sided inputs. J Theor Biol, 18(3):280-299.

[58]Lipp M, Scherzer D, Wonka P, et al., 2011. Interactive modeling of city layouts using layers of procedural content. Comput Graph Forum, 30(2):345-354.

[59]Lynch K, 1964. The Image of the City. MIT Press, Cambridge, UK.

[60]MacQueen J, 1967. Some methods for classification and analysis of multivariate observations. Proc 5th Berkeley Symp on Mathematical Statistics and Probability, p.281-297.

[61]Mathew CDT, Knob PR, Musse SR, et al., 2019. Urban walkability design using virtual population simulation. Comput Graph Forum, 38(1):455-469.

[62]Mvech R, Prusinkiewicz P, 1996. Visual models of plants interacting with their environment. Proc 23rd Annual Conf on Computer Graphics and Interactive Techniques, p.397-410.

[63]Merrell P, Schkufza E, Koltun V, 2010. Computer-generated residential building layouts. ACM Trans Graph, 29(6):181.

[64]Mirza M, Osindero S, 2014. Conditional generative adversarial nets. https://arxiv.org/abs/1411.1784

[65]Müller P, Wonka P, Haegler S, et al., 2006. Procedural modeling of buildings. ACM Trans Graph, 25(3):614-623.

[66]Musialski P, Wimmer M, Wonka P, 2012. Interactive coherence-based faccades modeling. Comput Graph Forum, 31(2pt3):661-670.

[67]Nan LL, Sharf A, Zhang H, et al., 2010. SmartBoxes for interactive urban reconstruction. ACM Trans Graph, 29(4):93.

[68]Nan LL, Jiang CG, Ghanem B, et al., 2015. Template assembly for detailed urban reconstruction. Comput Graph Forum, 34(2):217-228.

[69]Newton D, 2019. Generative deep learning in architectural design. Technol Arch Des, 3(2):176-189.

[70]Nishida G, Garcia-Dorado I, Aliaga DG, 2016a. Example-driven procedural urban roads. Comput Graph Forum, 35(6):5-17.

[71]Nishida G, Garcia-Dorado I, Aliaga DG, et al., 2016b. Interactive sketching of urban procedural models. ACM Trans Graph, 35(4):130.

[72]Parish YIH, Müller P, 2001. Procedural modeling of cities. Proc 28th Annual Conf on Computer Graphics and Interactive Techniques, p.301-308.

[73]Peng CH, Yang YL, Wonka P, 2014. Computing layouts with deformable templates. ACM Trans Graph, 33(4):99.

[74]Peng CH, Yang YL, Bao F, et al., 2016. Computational network design from functional specifications. ACM Trans Graph, 35(4):131.

[75]Rumelhart DE, Hinton GE, Williams RJ, 1986. Learning Internal Representations by Error Propagation. In: Rumelhart DE, McClelland JL (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1: Foundations. MIT Press, Cambridge, MA, USA.

[76]Schapire RE, 1999. A brief introduction to boosting. Proc 16th Int Joint Conf on Artificial Intelligenc, p.1401-1406.

[77]Scholkopf B, Smola AJ, 2001. Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press, Cambridge, MA, USA.

[78]Schwarz M, Müller P, 2015. Advanced procedural modeling of architecture. ACM Trans Graph, 34(4):107.

[79]Shen CH, Huang SS, Fu H, et al., 2011. Adaptive partitioning of urban facades. ACM Trans Graph, 30(6):184.

[80]Smelik RM, Tutenel T, Bidarra R, et al., 2014. A survey on procedural modelling for virtual worlds. Comput Graph Forum, 33(6):31-50.

[81]Smith N, Moehrle N, Goesele M, et al., 2018. Aerial path planning for urban scene reconstruction: a continuous optimization method and benchmark. ACM Trans Graph, 37(6):183.

[82]United Nations, 2018. 2018 Revision of World Urbanization Prospects. https://un.org/development/desa/publications/2018-revision-of-world-urbanization-prospects.html [Accessed on May 16, 2018]

[83]Vanegas CA, Aliaga DG, Benes B, et al., 2009. Interactive design of urban spaces using geometrical and behavioral modeling. ACM Trans Graph, 28(5):111.

[84]Vanegas CA, Aliaga DG, Benevs B, 2010. Building reconstruction using Manhattan-world grammars. Proc IEEE Computer Society Conf on Computer Vision and Pattern Recognition, p.358-365.

[85]Vanegas CA, Garcia-Dorado I, Aliaga DG, et al., 2012a. Inverse design of urban procedural models. ACM Trans Graph, 31(6):168.

[86]Vanegas CA, Kelly T, Weber B, et al., 2012b. Procedural generation of parcels in urban modeling. Comput Graph Forum, 31(2pt3):681-690.

[87]Verdie Y, Lafarge F, Alliez P, 2015. LOD generation for urban scenes. ACM Trans Graph, 34(3):30.

[88]Wonka P, Wimmer M, Sillion F, et al., 2003. Instant Architecture. ACM Press, New York, NY, USA.

[89]Wu FZ, Yan DM, Dong WM, et al., 2014. Inverse procedural modeling of facade layouts. ACM Trans Graph, 33(4):121.

[90]Wu WM, Fan LB, Liu LG, et al., 2018. MIQP-based layout design for building interiors. Comput Graph Forum, 37(2):511-521.

[91]Xiao JX, Fang T, Zhao P, et al., 2009. Image-based street-side city modeling. ACM Trans Graph, 28(5):114.

[92]Yang YL, Wang J, Vouga E, et al., 2013. Urban pattern: layout design by hierarchical domain splitting. ACM Trans Graph, 32(6):181.

[93]Yu QZ, Steed A, 2012. Example-based Road Network Synthesis. Eurographics 2012-Short Papers.

[94]Yumer ME, Asente P, Mech R, et al., 2015. Procedural modeling using autoencoder networks. Proc 28th Annual ACM Symp on User Interface Software and Technology, p.109-118.

[95]Zhang H, Xu K, Jiang W, et al., 2013. Layered analysis of irregular facades via symmetry maximization. ACM Trans Graph, 32(4):121.

[96]Zheng Q, Sharf A, Wan GW, et al., 2010. Non-local scan consolidation for 3D urban scenes. ACM Trans Graph, 29(4):94.

[97]Zhou B, Lapedriza A, Xiao J, et al., 2014. Learning deep features for scene recognition using places database. Proc 27th Int Conf on Neural Information Processing Systems, p.487-495.

[98]Zhu X, Goldberg AB, 2009. Introduction to semi-supervised learning. Synth Lect Artif Intell Mach Learn, 3(1):1-130.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2022 Journal of Zhejiang University-SCIENCE