Filters








2,108 Hits in 8.1 sec

Spatial Random Tree Grammars for Modeling Hierarchal Structure in Images with Regions of Arbitrary Shape

J. M. Siskind, J. Sherman, Jr, I. Pollak, M. P. Harper, C. A. Bouman
2007 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We present a novel probabilistic model for the hierarchical structure of an image and its regions. We call this model spatial random tree grammars (SRTGs).  ...  We apply our method to the task of classifying natural images and demonstrate that the addition of hierarchical structure significantly improves upon the performance of a baseline model that lacks such  ...  Another version of spatial random tree models and the center-surround algorithm was developed in [54] .  ... 
doi:10.1109/tpami.2007.1169 pmid:17627040 fatcat:eb7sm5zdkjgbpf74gobixcbzi4

Hierarchical Stochastic Image Grammars for Classification and Segmentation

W. Wang, I. Pollak, T.-S. Wong, C.A. Bouman, M.P. Harper, J.M. Siskind
2006 IEEE Transactions on Image Processing  
We develop a new class of hierarchical stochastic image models called spatial random trees (SRTs) which admit polynomial-complexity exact inference algorithms.  ...  The states at the tree nodes are random variables, and, in addition, the structure of the tree is random and is generated by a probabilistic grammar.  ...  Huang for their help and suggestions during the preparation of this manuscript.  ... 
doi:10.1109/tip.2006.877496 pmid:17022268 fatcat:h5ixaf3ejzfvtpyp4yifkuoz74

Using grammars for pattern recognition in images

Ricardo Wandré Dias Pedro, Fátima L. S. Nunes, Ariane Machado-Lima
2013 ACM Computing Surveys  
Some factors accountable for this increasing use regard its relatively simple understanding and its ability to represent some semantic pattern models found in images, both spatially and temporally.  ...  The results indicated that in some of the studies retrieved, manually created grammars were used to comply with a particular purpose.  ...  Spatial random tree grammars were used for pattern recognition in images.  ... 
doi:10.1145/2543581.2543593 fatcat:w2gi2ikoirfqlmbdjn5jtpnyuq

Obtaining structural descriptions of building façades

Petar Vracar, Igor Kononenko, Marko Robnik-Sikonja
2016 Computer Science and Information Systems  
The method segments an input image into a hierarchical structure of window candidates.  ...  We describe a method for learning and recognizing windows as basic structural elements of façades and organizing them into interpretable models of building façades.  ...  They used randomized decision forest classifiers to classify façade image regions. Then, a conditional random field is used to enforce spatial consistency between neighboring regions. Martinovic et al  ... 
doi:10.2298/csis150222062v fatcat:okmjbwa4fvhexaukbucwh35hmy

A connection between partial symmetry and inverse procedural modeling

Martin Bokeloh, Michael Wand, Hans-Peter Seidel
2010 ACM Transactions on Graphics  
(b) Symmetric regions are marked in red. (c) A set of symmetric curves that cuts the model into two pieces yields a docking site that corresponds to (d) a replacement operation.  ...  The extracted rules are then used to implement tools for semi-automatic shape modeling by example, which are demonstrated on a number of different example data sets.  ...  Acknowledgements The authors would like to thank Alexander Berner, Qi-Xing Huang, Matthias Hullin, and Leonidas Guibas for useful discussions, and Gerd Wolf for creating many of our example models.  ... 
doi:10.1145/1778765.1778841 fatcat:qeccgajgurgrhgsnxufk5jp3fa

A connection between partial symmetry and inverse procedural modeling

Martin Bokeloh, Michael Wand, Hans-Peter Seidel
2010 ACM SIGGRAPH 2010 papers on - SIGGRAPH '10  
(b) Symmetric regions are marked in red. (c) A set of symmetric curves that cuts the model into two pieces yields a docking site that corresponds to (d) a replacement operation.  ...  The extracted rules are then used to implement tools for semi-automatic shape modeling by example, which are demonstrated on a number of different example data sets.  ...  Acknowledgements The authors would like to thank Alexander Berner, Qi-Xing Huang, Matthias Hullin, and Leonidas Guibas for useful discussions, and Gerd Wolf for creating many of our example models.  ... 
doi:10.1145/1833349.1778841 fatcat:ma6tlkrcozd2rl6zww5xv62npe

A connection between partial symmetry and inverse procedural modeling

Martin Bokeloh, Michael Wand, Hans-Peter Seidel
2010 ACM Transactions on Graphics  
(b) Symmetric regions are marked in red. (c) A set of symmetric curves that cuts the model into two pieces yields a docking site that corresponds to (d) a replacement operation.  ...  The extracted rules are then used to implement tools for semi-automatic shape modeling by example, which are demonstrated on a number of different example data sets.  ...  Acknowledgements The authors would like to thank Alexander Berner, Qi-Xing Huang, Matthias Hullin, and Leonidas Guibas for useful discussions, and Gerd Wolf for creating many of our example models.  ... 
doi:10.1145/1833351.1778841 fatcat:csehgpy5bzf3lky6a76ok53s4y

3D Design and Modeling of Smart Cities from a Computer Graphics Perspective

Daniel G. Aliaga
2012 ISRN Computer Graphics  
Modeling cities, and urban spaces in general, is a daring task for computer graphics, computer vision, and visualization.  ...  In particular, we divide research in modeling cities and urban spaces into the areas of geometrical modeling and of behavioral modeling.  ...  [10] propose a general grammarbased structure for an arbitrary building (Figure 9 ).  ... 
doi:10.5402/2012/728913 fatcat:6sevbn6rcreyrnib7a7pmif72i

Recursive Segmentation and Recognition Templates for 2D Parsing

Leo Zhu, Yuanhao Chen, Yuan Lin, Chenxi Lin, Alan L. Yuille
2008 Neural Information Processing Systems  
In this paper, we propose a Hierarchical Image Model (HIM) for 2D image parsing which outputs image segmentation and object recognition.  ...  Language and image understanding are two major goals of artificial intelligence which can both be conceptually formulated in terms of parsing the input signal into a hierarchical representation.  ...  In our case, X is a set of images, with Y being a set of possible parse trees which specify the labels of image regions in a hierarchical form.  ... 
dblp:conf/nips/ZhuCLLY08 fatcat:lkb7jdcuonbqtbq2nzwwt4quhq

An Inverse Procedural Modeling Pipeline for SVBRDF Maps [article]

Yiwei Hu, Chengan He, Valentin Deschaintre, Julie Dorsey, Holly Rushmeier
2021 arXiv   pre-print
Given Spatially-Varying Bidirectional Reflectance Distribution Functions (SVBRDFs) represented as sets of pixel maps, our pipeline decomposes them into a tree of sub-materials whose spatial distributions  ...  Spatial distributions of these sub-materials are modeled either by a by-example inverse synthesis method recovering Point Process Texture Basis Functions (PPTBF) or via random sampling.  ...  Abhijeet Ghosh with his EPSRC Early Career Fellowship (EP/N006259/1)  ... 
arXiv:2109.06395v2 fatcat:wf76533irncjvpc466lvgfqtka

A Stochastic Grammar of Images

Song-Chun Zhu, David Mumford
2006 Foundations and Trends in Computer Graphics and Vision  
This exploratory paper quests for a stochastic and context sensitive grammar of images.  ...  The proposal grammar integrates three prominent representations in the literature: stochastic grammars for composition, Markov (or graphical) models for contexts, and sparse coding with primitives (wavelets  ...  Stuart Geman, Yingnian Wu, Harry Shum, Alan Yuille, and Joachim Buhmann for their extensive discussions and helpful comments. The first author also thanks many students at UCLA  ... 
doi:10.1561/0600000018 fatcat:4gicslrfufabratzlxeiz275nm

Recursive segmentation and recognition templates for image parsing

Long Zhu, Yuanhao Chen, Yuan Lin, Chenxi Lin, A. Yuille
2012 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we propose a Hierarchical Image Model (HIM) for 2D image parsing which outputs image segmentation and object recognition.  ...  Language and image understanding are two major goals of artificial intelligence which can both be conceptually formulated in terms of parsing the input signal into a hierarchical representation.  ...  In our case, the inputs {I i } are a set of images, and the outputs {W i } are a set of parse trees which specify the labels of image regions in a hierarchical form.  ... 
doi:10.1109/tpami.2011.160 pmid:22193662 fatcat:wiwmngxcazb7fjgdhuobdmoggq

Complexity formalisms, order and disorder in the structure of art [chapter]

Mark W. Davis
1997 Lecture Notes in Computer Science  
Experiments in the automatic production of aural and visual artworks are described that utilize this theory to select, within an evolutionary model, among a population of rules systems for those that occupy  ...  Order and disorder appear to be opposite extremes in a spectrum of structural types, yet they both contain little that is intuitively complex.  ...  random resulting in trees shaped like spherical pincushions.  ... 
doi:10.1007/bfb0014796 fatcat:ld2xbj4xxvdw7odw46zp2g3pjy

Unsupervised learning of hierarchical spatial structures in images

Devi Parikh, C. Lawrence Zitnick, Tsuhan Chen
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
In this work, we present a unified approach to unsupervised learning of hierarchical spatial structures from a collection of images.  ...  These classes of spatial structures are inherently hierarchical in nature. Although seemingly quite different these spatial patterns are simply manifestations of different levels in a hierarchy.  ...  Conclusion In this paper, we proposed an unsupervised method for learning hierarchical spatial structures in images.  ... 
doi:10.1109/cvpr.2009.5206549 dblp:conf/cvpr/ParikhZC09 fatcat:ayupryrfmbhwzgszipa4o6fupi

Unsupervised learning of hierarchical spatial structures in images

D. Parikh, C.L. Zitnick, Tsuhan Chen
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
In this work, we present a unified approach to unsupervised learning of hierarchical spatial structures from a collection of images.  ...  These classes of spatial structures are inherently hierarchical in nature. Although seemingly quite different these spatial patterns are simply manifestations of different levels in a hierarchy.  ...  The unsupervised approach is shown to discover categories in images containing just one object, as well as multiple objects.  ... 
doi:10.1109/cvprw.2009.5206549 fatcat:hnhjebqouncw7mr4ivu2tudjmu
« Previous Showing results 1 — 15 out of 2,108 results