Filters








1,177 Hits in 5.5 sec

Divide and Conquer: Subset Matching for Scene Graph Generation in Complex Scenes

Xin Lin, Jinquan Zeng, Xingquan Li
2022 IEEE Access  
Object occlusion is a critical challenge when generating scene graphs in complex scenes. However, this issue has rarely been explored in recent works.  ...  The goal of scene graph generation (SGG) is to classify objects and their pair-wise relationships in a visual scene.  ...  more robust for generating scene graphs in complex scenes.  ... 
doi:10.1109/access.2022.3165617 fatcat:7raleom6ffhv5caw3objdq6av4

Supporting divide-and-conquer algorithms for image processing

Quentin F. Stout
1987 Journal of Parallel and Distributed Computing  
Divide-and-conquer is an important algorithm strategy, but it is not widely used in image processing.  ...  of divide-and-conquer algorithms.  ...  However, as research advances into using parallel computers for higher-level tasks such as scene recognition or image understanding, it seems that divide-and-conquer will become increasingly useful.  ... 
doi:10.1016/0743-7315(87)90010-4 fatcat:cy2aq4y7rrehfngdfxqdvdeu3q

Divide and Conquer: Hierarchical Reinforcement Learning and Task Decomposition in Humans [chapter]

Carlos Diuk, Anna Schapiro, Natalia Córdova, José Ribas-Fernandes, Yael Niv, Matthew Botvinick
2013 Computational and Robotic Models of the Hierarchical Organization of Behavior  
However, the simple forms of RL considered in most empirical research do not scale well, making their relevance to complex, real-world behavior unclear.  ...  In computational RL, one strategy for addressing the scaling problem is to introduce hierarchical structure, an approach that has intriguing parallels with human behavior.  ...  In order to set the scene for our own research in this area, we can consider two general approaches, one based on frequency and the other on problem structure.  ... 
doi:10.1007/978-3-642-39875-9_12 fatcat:mshwwifldjcjpivldfvju623fa

Novel parallel algorithm for constructing Delaunay triangulation based on a twofold-divide-and-conquer scheme

Wenzhou Wu, Yikang Rui, Fenzhen Su, Liang Cheng, Jiechen Wang
2014 GIScience & Remote Sensing  
Next, the Guibas-Stolfi divide-and-conquer algorithm is applied to construct Delaunay subtriangulations in each subset. Finally, the sub-triangulations are merged based on the binary tree.  ...  To increase the efficiency when processing large data sets, a novel parallel algorithm is proposed for constructing the Delaunay triangulation of a planar point set based on a twofold-divide-and-conquer  ...  Funding This work is supported by the National Natural Science Foundation of China [grant number 41371017] and the Program for New Century Excellent Talents in University (NCET-13-0280).  ... 
doi:10.1080/15481603.2014.946666 fatcat:jx6l4qc3xfbdfbe2xt4pnt6wcy

Arc consistency for factorable relations

Mark Perlin
1992 Artificial Intelligence  
In this paper, we present conditions and mechanisms for such transformations, and show how to factor relations into more manageable components.  ...  An optimal arc consistency algorithm AC-4 was given by Mohr and Henderson [8]. AC-4 has cost 0(ea 2 ), and cost (na 2 ) for scene labelling.  ...  Such factorizations appear in other divide-and-conquer [5] algorithms.  ... 
doi:10.1016/0004-3702(92)90077-b fatcat:zjovv6inxzewdmku4agk2tt52m

MSClique: Multiple Structure Discovery through the Maximum Weighted Clique Problem

Gerard Sanroma, Adrian Penate-Sanchez, René Alquézar, Francesc Serratosa, Francesc Moreno-Noguer, Juan Andrade-Cetto, Miguel Ángel González Ballester, Pew-Thian Yap
2016 PLoS ONE  
We present a novel approach for feature correspondence and multiple structure discovery in computer vision.  ...  We demonstrate the effectiveness of our method in multiple-structure fitting experiments in both publicly available and in-house datasets.  ...  Acknowledgments Authors would also like to thank Oscar Sanromà and Esther Valldosera for their help in the preparation of the book dataset. The first author is co-financed by the Marie Curie  ... 
doi:10.1371/journal.pone.0145846 pmid:26766071 pmcid:PMC4713099 fatcat:agwzbyrqa5bkzmiwictk72swim

Naive ray-tracing

Benjamin Mora
2011 ACM Transactions on Graphics  
This is possible with a modification of Whitted's naive ray-tracing algorithm by using a divide-and-conquer approach, and by having a sufficient collection of rays in order to reduce the complexity of  ...  We present an efficient ray-tracing algorithm which, for the first time, does not store any data structures when performing spatial subdivisions, and directly computes intersections inside the scene.  ...  ACKNOWLEDGMENTS We would like to thank Sally Andrew for proof-reading of the article and the reviewers for their valuable feedback.  ... 
doi:10.1145/2019627.2019636 fatcat:cm5yrlvv25hthadgf6kqpglyzq

Multi-view Geometry Compression [chapter]

Siyu Zhu, Tian Fang, Runze Zhang, Long Quan
2015 Lecture Notes in Computer Science  
We first construct an image quality graph, in which each vertex represents an input image, and the problem is then to determine a connected sub-graph guaranteeing a consistent reconstruction and maximizing  ...  For large-scale and highly redundant photo collections, eliminating statistical redundancy in multi-view geometry is of great importance to efficient 3D reconstruction.  ...  We really appreciate the support of RGC-GRF 618711, RGC/NSFC N HKUST607/11, ITC-PSKL12EG02, and National Basic Research Program of China (2012CB316300).  ... 
doi:10.1007/978-3-319-16808-1_1 fatcat:meg7fxcwj5hr3llck3peyqzezi

Exploiting manifold geometry in hyperspectral imagery

C.M. Bachmann, T.L. Ainsworth, R.A. Fusina
2005 IEEE Transactions on Geoscience and Remote Sensing  
We divide the scene into a set of smaller tiles. The manifolds derived from the individual tiles are then aligned and stitched together to recomplete the scene.  ...  A new algorithm for exploiting the nonlinear structure of hyperspectral imagery is developed and compared against the de facto standard of linear mixing.  ...  All of these approaches relied on the ability to divide, conquer, and merge smaller subsets of the remote sensing data.  ... 
doi:10.1109/tgrs.2004.842292 fatcat:mqhoprk7dffm7daplzymyymrzm

Manhattan-World Urban Reconstruction from Point Clouds [chapter]

Minglei Li, Peter Wonka, Liangliang Nan
2016 Lecture Notes in Computer Science  
Manhattan-world urban scenes are common in the real world. We propose a fully automatic approach for reconstructing such scenes from 3D point samples.  ...  Our key idea is to represent the geometry of the buildings in the scene using a set of well-aligned boxes. We first extract plane hypothesis from the points followed by an iterative refinement step.  ...  Acknowledgements We thank the reviewers for their valuable comments. We also thank Dr. Neil Smith for providing us the data used in Figure 7 .  ... 
doi:10.1007/978-3-319-46493-0_4 fatcat:havbpt6zdvallpag5h5tgtadpm

A Review of Segmentation Technology Based on 3D Point Cloud

Wang Xu, Liu Baolong
2021 International Journal of Advanced Network, Monitoring, and Controls  
In recent years, with the dramatic increase of polygon complexity of model, the advantage of point model becomes more and more obvious.  ...  Point cloud is an important data format that can completely express scene information.  ...  It can achieve the best performance without prior knowledge and can be used for more complex image segmentation, such as natural scenes, coins, medical images, etc.  ... 
doi:10.21307/ijanmc-2021-006 fatcat:sk23otv4vzfbbmeq5thgrjoyeu

Extending the scene graph with a dataflow visualization system

Michael Kalkusch, Dieter Schmalstieg
2006 Proceedings of the ACM symposium on Virtual reality software and technology - VRST '06  
Dataflow graphs are a very successful paradigm in scientific visualization, while scene graphs are a leading approach in interactive graphics and virtual reality.  ...  mechanism for dynamically building and evaluating dataflow.  ...  This may not always be desirable given that the nodes involved come from different parts of a scene graph, as it prevents a divide and conquer strategy from being used to model the overall scene graph.  ... 
doi:10.1145/1180495.1180547 dblp:conf/vrst/KalkuschS06 fatcat:zbfxaedlf5a3nn2fgnipjfd5ri

Keyframe-based monocular SLAM: design, survey, and future directions

Georges Younes, Daniel Asmar, Elie Shammas, John Zelek
2017 Robotics and Autonomous Systems  
Extensive research in the field of monocular SLAM for the past fifteen years has yielded workable systems that found their way into various applications in robotics and augmented reality.  ...  , highly dynamic motion, poorly textured scenes, repetitive textures, map maintenance, and failure recovery.  ...  To decrease the computational complexity and to maintain only the strongest features, the frame is divided into a grid, and only the strongest feature per grid cell is used.  ... 
doi:10.1016/j.robot.2017.09.010 fatcat:b6ilgshsinckjdnlsozmjppkly

GPDOF — A FAST ALGORITHM TO DECOMPOSE UNDER-CONSTRAINED GEOMETRIC CONSTRAINT SYSTEMS: APPLICATION TO 3D MODELING

GILLES TROMBETTONI, MARTA WILCZKOWIAK
2006 International journal of computational geometry and applications  
The constraint system is decomposed in a few seconds, and can then be solved in hundredths of second.  ...  Our approach exploits a general-purpose decomposition algorithm, called GPDOF, and a dictionary of very efficient solving procedures, called r-methods, based on theorems of geometry.  ...  Thanks to David Daney, Bertrand Neveu and Théodore Papadopoulo for useful discussions. Thanks to Gilles Chabert for comments. Thanks to Mr. Dominique Chancel for the architectural drawings.  ... 
doi:10.1142/s0218195906002154 fatcat:dvstagz2q5fdhbshgfgd2yiwza

Spatiotemporal Bundle Adjustment for Dynamic 3D Human Reconstruction in the Wild [article]

Minh Vo, Yaser Sheikh, Srinivasa G. Narasimhan
2020 arXiv   pre-print
This algorithm is further made more efficient by a divide and conquer scheme while still maintaining high accuracy.  ...  Bundle adjustment jointly optimizes camera intrinsics and extrinsics and 3D point triangulation to reconstruct a static scene.  ...  Divide and Conquer While the incremental reconstruction and alignment approach offers a tractable solution for the loss function defined in Eq .3, its complexity increases quadratically with the number  ... 
arXiv:2007.12806v1 fatcat:qs4dpgcge5akhacwjhfttvojb4
« Previous Showing results 1 — 15 out of 1,177 results