Urban Scene Segmentation, Recognition and Remodeling. Part III. Jinglu Wang 11/24/2016 ACCV 2016 TUTORIAL
|
|
- Christopher Eaton
- 5 years ago
- Views:
Transcription
1 Part III Jinglu Wang Urban Scene Segmentation, Recognition and Remodeling 102
2 Outline Introduction Related work Approaches Conclusion and future work o o - - ) 11/7/16 103
3 Introduction Motivation Motivation Large-scale multi-view reconstruction 3D city models are available 11/7/16 104
4 Introduction Motivation Motivation How large is the area of vegetation? How many buildings are there? Where is the library? What is this?? 11/7/16 105
5 Introduction Motivation Motivation Semantic meaning of objects (concept model) 11/7/16 106
6 Introduction Motivation Motivation Semantic meaning Refine Practical applications Change visualization Energy modeling Neighbor analysis Line of sight Estate modeling Flood simulation Geometry Building Tree 11/7/16 107
7 Introduction Overview Findings Semantic meanings Object level Refine models Framework Semantic Segmentation Object Recognition Object Remodeling 11/7/16 108
8 Introduction Overview Framework Semantic Segmentation Object Recognition Object Remodeling (d) Building abstraction (b) Object level segmentation (a) Joint semantic segmentation (e) Building regularization (c) Façade recognition (g) Facade modeling 11/7/16 109
9 Outline Introduction Related work Approaches Conclusion o o o )) - ( /7/16 110
10 Related Work With Laser scanned data o [Lafarge et al. 2012] o Accurate geometry No photometric information [Mateiet al. 2008] [Lin et al. 2013] With multi-view reconstructed data [Yannick et al., 2015] [Julien et al. 2013] [Xiao et al. 2009] 11/7/16 111
11 Outline Introduction Related work Approaches Conclusion 11/7/16 112
12 Approaches 11/7/16 113
13 Semantic Segmentation Joint Semantic Segmentation Joint Semantic Segmentation Challenge Representation Workflow Result Evaluation 11/7/16 114
14 Semantic Segmentation Joint Semantic Segmentation Challenges Joint 2D 3D 2D-3D consistency Efficient labeling 11/7/16 115
15 Semantic Segmentation Joint Semantic Segmentation Input Multi-view reconstruction Multi-view images 11/7/16 116
16 Semantic Segmentation Joint Semantic Segmentation Label Consistency for Joint Segmentation Cam A Cam B Cam A Cam B Multi-view reconstruction Tree Building Multi-view label consistency 11/7/16 117
17 Semantic Segmentation Joint Semantic Segmentation Correspondence Graph Patch segmentation Graph visualization 11/7/16 118
18 Semantic Segmentation Joint Semantic Segmentation Correspondence Graph Patch segmentation Graph visualization 11/7/16 119
19 Semantic Segmentation Joint Semantic Segmentation Correspondence Graph Graph visualization Photometric features V 2d I 1 E 2d I 2 E p E 3d V 3d M Geometric features 11/7/16 120
20 Semantic Segmentation Joint Semantic Segmentation Workflow Automatic training data generation Patch segmentation Training data initialization Training data validation Joint Segmentation mislabeled 11/7/16 121
21 Semantic Segmentation Joint Semantic Segmentation Workflow Automatic training data generation Patch segmentation Training data initialization Training data validation Joint Segmentation mislabeled Patch-based representation [Liu & Wang 2015] 11/7/16 122
22 Semantic Segmentation Joint Semantic Segmentation Workflow Automatic training data generation Patch segmentation Training data initialization Training data validation Joint Segmentation mislabeled 11/7/16 123
23 Semantic Segmentation Joint Semantic Segmentation Training Data Initialization Feature Planarity Relative altitude Horizontality Area Category Ground Roof Facade Vegetation Training data initialization result Good or bad? Roof Facade Ground vegetation 11/7/16 124
24 Semantic Segmentation Joint Semantic Segmentation Workflow Automatic training data generation Patch segmentation Training data initialization Training data validation Joint Segmentation mislabeled 11/7/16 125
25 Semantic Segmentation Joint Semantic Segmentation Training Data Validation Validation Conditional Random Field (CRF) I 1 V 2d E 2d I2 E p E 3d V 3d M Data term L = { l, l } good bad Smoothness term Correspondence term 11/7/16 126
26 Semantic Segmentation Joint Semantic Segmentation Training Data Validation Data term: labeling confidence based on cross-validation 50% Train 50% Test 50% Test 50% Test y = -1 Samples y = +1 (a) Initialize k: the times of being validated (b) Test (c) Validate 11/7/16 127
27 Semantic Segmentation Joint Semantic Segmentation Training Data Validation Result Identified mislabeled sample Scanned data MVS data (a) Input (b) Initial (c) Validated 11/7/16 128
28 Semantic Segmentation Joint Semantic Segmentation Joint Segmentation Results Apply similar CRF over the correspondence graph V 2d I 1 I 2 E 2d E p L = { categories} E 3d V 3d M (a) Joint segmentation result with MVS data (b) Joint segmentation result with scanned data 11/7/16 129
29 Semantic Segmentation Joint Semantic Segmentation Evaluation Evaluation of the automatically generated training data Evaluation of the parsing performance achieved by the automatically generated training data 11/7/16 130
30 Semantic Segmentation Joint Semantic Segmentation Evaluation Evaluation of the automatically generated training data Evaluation of the parsing performance achieved by the automatically generated training data Purity of training data Images 3D data building ground sky tree clutter 0 building ground tree clutter Initialized training data Cleaned training data 11/7/16 131
31 Semantic Segmentation Joint Semantic Segmentation Evaluation Evaluation of the automatically generated training data Evaluation of the parsing performance achieved by the automatically generated training data Table 3.4: Comparison with manually labeled data Table 3.5: Comparison with previous method 11/7/16 132
32 Semantic Segmentation Joint Semantic Segmentation Contributions Patch based representation Automatic training data generation Model multi-view label consistency 11/7/16 133
33 Framework 11/7/16 134
34 Object Recognition Object Level Segmentation Object Level Segmentation Motivation Objects are not separated Category-level segmentation are not precise enough? Error! 11/7/16 135
35 Object Recognition Object Level Segmentation Object Level Segmentation Terrain extraction Urban object classification 2D map consolidation segmentation 2D to 3D 11/7/16 136
36 Object Recognition Object Level Segmentation Object Level Segmentation Terrain extraction Urban object classification 2D map consolidation segmentation 2D to 3D 1 0 (a) Height map (b) Over-segmented map (c) Final segmented map 11/7/16 137
37 Object Recognition Object Level Segmentation Object Level Segmentation Terrain extraction Urban object classification 2D map consolidation segmentation 2D to 3D (a) Segmented roofs (b) Flooding illustration (c) Segmented objects 11/7/16 138
38 Object Recognition Object Level Segmentation Object Level Segmentation Results 11/7/16 139
39 Object Remodeling Building Abstraction Building Abstraction Motivation Surface Wireframe Zoom in Segmented input Redundant, noisy, not visually pleasing! Abstracted 11/7/16 140
40 Object Remodeling Building Abstraction Contour Abstraction (a) (a) Input contours Higher order CRF formulation (b) Labeled contour points (c) Abstracted contours Higher order regularity Higher order regularity term 11/7/16 141
41 Object Remodeling Building Abstraction Results and Evaluation (a) Input of SF (b) Abstraction of SF Save 94% storage (c) Abstraction of CityA Table 5.1: Building object abstraction statistics 11/7/16 142
42 Object Remodeling Building Abstraction Contributions Segmentation at the object level Higher order CRF encodes global regularities 11/7/16 143
43 Framework 11/7/16 144
44 Object Recognition Façade Recognition Existing Methods Bottom-up Combination Top-down Lack of effective object-level modeling Lack of generality in irregular facade structure representation Translation symmetry [Zhao et al. 2011] Rank-one approximation [Yang et al. 2012] Three layers [Martinovic et al. 2012] Shape grammar Irregular lattice [Teboul et al. 2011] [Riemensheneider et al. 2012] Interactions between objects? Noise? Irregular structure? 11/7/16 145
45 Object Recognition Façade Recognition Our Approach (a) input image; (b) object (window) probability map; (c) 2D incomplete grid facade structure representation. (d) regulation result using a multi-lattice structure. 11/7/16 146
46 Object Recognition Façade Recognition An Object-level Model A marked point process model (MPP) Sparsely populated objects 11/7/16 147
47 Object Recognition Façade Recognition Energy Function 11/7/16 148
48 Object Recognition Façade Recognition Energy Function Rectangle Rate Contrast Rate Homogeneity Rate Area Rate 11/7/16 149
49 Object Recognition Façade Recognition Structure-driven MCMC Optimization The energy function is not convex Large solution space Multiple-birth-and-death (MBD) algorithm Ground truth Candidate 11/7/16 150
50 Object Recognition Façade Recognition Structure-driven Multiple-birth-anddeath (MBD) Previous iterations Birth Death Current iteration Obtained Lattice-driven MBD Proposed Removed Grid-driven MBD 11/7/16 151
51 Object Recognition Façade Recognition Results Laser scans Single image 11/7/16 152
52 Object Recognition Façade Recognition Application - Grammar Factorization Grammar factorization using detected windows Input image Remodeled Textured Rendering result of block data 11/7/16 153
53 Object Recognition Façade Recognition Evaluation Table 4.1: Comparison with other methods LR : short for with low rank constraint. Gr : is short for using grammar constraints 11/7/16 154
54 Object Recognition Façade Recognition Contributions A general facade structure representation A marked point process model to model sparsely populated objects in man-made scenes A structure-driven Markov Cain Mote Carlo (MCMC) optimization 11/7/16 155
55 Framework v v 11/7/16 156
56 Object Remodeling Building Regularization Problem Noisy, incomplete, distorted structure! Input MVS model Textured MVS model Simplified model 11/7/16 157
57 Object Remodeling Building Regularization Image-based Building Scaffolding Regularize 11/7/16 158
58 Object Remodeling Building Regularization Image-based Building Scaffolding Regularize 11/7/16 159
59 Object Remodeling Building Regularization Workflow Automatic phase Interactive phase View Selection Automatic Joint 2D- 3D Line Proposal Surface Scaffold Structure Consolidation Interactive Structure-driven Scaffolding Iteratively 11/7/16 160
60 Object Remodeling Building Regularization Workflow Automatic phase Interactive phase View Selection Automatic Joint 2D- 3D Line Proposal Surface Scaffold Structure Consolidation Interactive Structure-driven Scaffolding Iteratively 11/7/16 161
61 Object Remodeling Building Regularization Surface Scaffold Structure 1 P 0 I F 1 l 1 L 1 1 P 1 d < e d (a) Input mesh M and 3D linear feature set F (b) Scaffold S 11/7/16 162
62 Object Remodeling Building Regularization Scaffold Topology Representation LPW relation types Contiguous relation Incident relation Parallel relation Other relation 11/7/16 163
63 Object Remodeling Building Regularization Scaffold Topology Representation LPW relation types Contiguous relation Incident relation Parallel relation Other relation 11/7/16 164
64 Object Remodeling Building Regularization Scaffold Topology Consolidation LPW relation types Contiguous relation Incident relation Parallel relation Other relation Incident clique Parallel clique Interaction between relation cliques 11/7/16 165
65 Object Remodeling Building Regularization Scaffold Topology Consolidation LPW relation types Contiguous relation Incident relation Parallel relation Other relation Incident clique Parallel clique Interaction between relation cliques 11/7/16 166
66 Object Remodeling Building Regularization Scaffold Topology Consolidation Relation conflict Formulation 11/7/16 167
67 Object Remodeling Building Regularization Global Shape Refinement 11/7/16 168
68 Object Remodeling Building Regularization Interactive Line Proposal (a) Symmetric joint structure (b) An line proposal iteration 11/7/16 169
69 Object Remodeling Building Regularization Result 11/7/16 170
70 Object Remodeling Building Regularization Application - Simplification 11/7/16 171
71 Object Remodeling Building Regularization Evaluation on Defect Laden Data 11/7/16 172
72 Object Remodeling Building Regularization More Results 11/7/16 173
73 Object Remodeling Building Regularization Contributions A novel scaffold structure A noise-insensitive scaffold structure consolidation method The interactive line proposal using urban priors 11/7/16 174
74 Outline Introduction Related work Approaches Conclusion and future work 11/7/16 175
75 Conclusion 11/7/16 176
76 Future Work Semantic segmentation Deep learning techniques àdeal with diverse datasets Online data driven learning methods àadapt to crowd sourcing platforms Object recognition Recognize individual tree models Parsing facades in large-scale Remodeling More complex primitives (quadratic features) 11/7/16 177
77 Publication Wang, J., Fang, T., Su, Q., Zhu, S., Liu, J., Cai, S., Tai, C., Quan, L. Image-based Building Regularization Using Structural Linear Features. IEEE Transactions on Visualization and Computer Graphics (TVCG) 2015 Wang, J., Liu, C., Shen, T., Quan, L. Structure-driven Facade Parsing With Irregular Patterns. Asian Conference on Pattern Recognition (ACPR) (Oral) Wang, J., Li, S., Zhang, H., Quan, L. Semantic Segmentation of Large-Scale Urban 3D Data with Low Annotation Cost. Computer Vision and Pattern Recognition (CVPR) Workshop Liu, J. Wang, J., Fang, T., Tai, C., Quan, L. Higher-order CRF Structural Segmentation of 3D Reconstructed Surfaces. International Conference on Computer Vision (ICCV) Zhang, H., Wang, J., Fang, T., Quan, L. Joint Segmentation of Images and Scanned Point Cloud in Large-Scale Street Scenes with Low Annotation Cost. IEEE Transactions On IMAGE PROCESSING 2014 (TIP) Zhang, H., Wang, J., Tan, P., Wang, J., Quan, L. Learning CRFs for Image Parsing with Adaptive Subgradient Descent. IEEE International Conference on Computer Vision (ICCV) Shen, T., Wang, J., Fang, T., Quan, L. Color Correction for Image-Based Modeling in the Large. Asian Conference on Computer Vision (ACCV) (To be appeared). 11/7/16 178
78 References Verdie, Y., Lafarge, F., & Alliez, P. (2015). LOD Generation for urban scenes(no. EPFL- ARTICLE ). Association for Computing Machinery. Valentin, J., Sengupta, S., Warrell, J., Shahrokni, A., & Torr, P. (2013). Mesh based semantic modelling for indoor and outdoor scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp ). Xiao, J., Fang, T., Zhao, P., Lhuillier, M., & Quan, L. (2009, December). Image-based street-side city modeling. In ACM Transactions on Graphics (TOG) (Vol. 28, No. 5, p. 114). ACM. Matei, B. C., Sawhney, H. S., Samarasekera, S., Kim, J., & Kumar, R. (2008, June). Building segmentation for densely built urban regions using aerial lidar data. In Computer Vision and Pattern Recognition, CVPR IEEE Conference on (pp. 1-8). IEEE. Lafarge, F., & Mallet, C. (2012). Creating large-scale city models from 3D-point clouds: a robust approach with hybrid representation. International journal of computer vision, 99(1), Lin, H., Gao, J., Zhou, Y., Lu, G., Ye, M., Zhang, C.,... & Yang, R. (2013). Semantic decomposition and reconstruction of residential scenes from lidar data. ACM Transactions on Graphics (TOG), 32(4), /7/16 179
79 Thanks! Questions? 11/7/16 180
Image-Based Buildings and Facades
Image-Based Buildings and Facades Peter Wonka Associate Professor of Computer Science Arizona State University Daniel G. Aliaga Associate Professor of Computer Science Purdue University Challenge Generate
More informationA DATA DRIVEN METHOD FOR FLAT ROOF BUILDING RECONSTRUCTION FROM LiDAR POINT CLOUDS
A DATA DRIVEN METHOD FOR FLAT ROOF BUILDING RECONSTRUCTION FROM LiDAR POINT CLOUDS A. Mahphood, H. Arefi *, School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran,
More informationComplete Residential Urban Area Reconstruction from Dense Aerial LiDAR Point Clouds
Complete Residential Urban Area Reconstruction from Dense Aerial LiDAR Point Clouds Qian-Yi Zhou, Ulrich Neumann University of Southern California Abstract We present an automatic system to reconstruct
More informationHuman Upper Body Pose Estimation in Static Images
1. Research Team Human Upper Body Pose Estimation in Static Images Project Leader: Graduate Students: Prof. Isaac Cohen, Computer Science Mun Wai Lee 2. Statement of Project Goals This goal of this project
More informationTranslation Symmetry Detection: A Repetitive Pattern Analysis Approach
2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops Translation Symmetry Detection: A Repetitive Pattern Analysis Approach Yunliang Cai and George Baciu GAMA Lab, Department of Computing
More informationBUILDING DETECTION AND STRUCTURE LINE EXTRACTION FROM AIRBORNE LIDAR DATA
BUILDING DETECTION AND STRUCTURE LINE EXTRACTION FROM AIRBORNE LIDAR DATA C. K. Wang a,, P.H. Hsu a, * a Dept. of Geomatics, National Cheng Kung University, No.1, University Road, Tainan 701, Taiwan. China-
More informationFOOTPRINTS EXTRACTION
Building Footprints Extraction of Dense Residential Areas from LiDAR data KyoHyouk Kim and Jie Shan Purdue University School of Civil Engineering 550 Stadium Mall Drive West Lafayette, IN 47907, USA {kim458,
More informationImproving Latent Fingerprint Matching Performance by Orientation Field Estimation using Localized Dictionaries
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,
More informationAUTOMATIC EXTRACTION OF BUILDING FEATURES FROM TERRESTRIAL LASER SCANNING
AUTOMATIC EXTRACTION OF BUILDING FEATURES FROM TERRESTRIAL LASER SCANNING Shi Pu and George Vosselman International Institute for Geo-information Science and Earth Observation (ITC) spu@itc.nl, vosselman@itc.nl
More informationFeature Fusion for Registering Wide-baseline Urban Images
Feature Fusion for Registering Wide-baseline Urban Images Quan Wang, Suya You Computer Science Department University of Southern California Los Angeles, California, U.S.A. {quanwang, suyay} @graphics.usc.edu
More informationRegularized 3D Modeling from Noisy Building Reconstructions
Regularized 3D Modeling from Noisy Building Reconstructions Thomas Holzmann Friedrich Fraundorfer Horst Bischof Institute for Computer Graphics and Vision, Graz University of Technology, Austria {holzmann,fraundorfer,bischof}@icg.tugraz.at
More informationNATIONWIDE POINT CLOUDS AND 3D GEO- INFORMATION: CREATION AND MAINTENANCE GEORGE VOSSELMAN
NATIONWIDE POINT CLOUDS AND 3D GEO- INFORMATION: CREATION AND MAINTENANCE GEORGE VOSSELMAN OVERVIEW National point clouds Airborne laser scanning in the Netherlands Quality control Developments in lidar
More informationManhattan-world Urban Reconstruction from Point Clouds
Manhattan-world Urban Reconstruction from Point Clouds Minglei Li 1,2, Peter Wonka 1, and Liangliang Nan 1 1 Visual Computing Center, KAUST, Saudi Arabia {mingleili87, liangliang.nan, pwonka}@gmail.com
More informationReconstruction of Polygonal Faces from Large-Scale Point-Clouds of Engineering Plants
1 Reconstruction of Polygonal Faces from Large-Scale Point-Clouds of Engineering Plants Hiroshi Masuda 1, Takeru Niwa 2, Ichiro Tanaka 3 and Ryo Matsuoka 4 1 The University of Electro-Communications, h.masuda@euc.ac.jp
More informationUnwrapping of Urban Surface Models
Unwrapping of Urban Surface Models Generation of virtual city models using laser altimetry and 2D GIS Abstract In this paper we present an approach for the geometric reconstruction of urban areas. It is
More informationStructured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov
Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter
More informationHybrid Textons: Modeling Surfaces with Reflectance and Geometry
Hybrid Textons: Modeling Surfaces with Reflectance and Geometry Jing Wang and Kristin J. Dana Electrical and Computer Engineering Department Rutgers University Piscataway, NJ, USA {jingwang,kdana}@caip.rutgers.edu
More informationFACET SHIFT ALGORITHM BASED ON MINIMAL DISTANCE IN SIMPLIFICATION OF BUILDINGS WITH PARALLEL STRUCTURE
FACET SHIFT ALGORITHM BASED ON MINIMAL DISTANCE IN SIMPLIFICATION OF BUILDINGS WITH PARALLEL STRUCTURE GE Lei, WU Fang, QIAN Haizhong, ZHAI Renjian Institute of Surveying and Mapping Information Engineering
More informationAUTOMATIC GENERATION OF DIGITAL BUILDING MODELS FOR COMPLEX STRUCTURES FROM LIDAR DATA
AUTOMATIC GENERATION OF DIGITAL BUILDING MODELS FOR COMPLEX STRUCTURES FROM LIDAR DATA Changjae Kim a, Ayman Habib a, *, Yu-Chuan Chang a a Geomatics Engineering, University of Calgary, Canada - habib@geomatics.ucalgary.ca,
More informationOutline of Presentation. Introduction to Overwatch Geospatial Software Feature Analyst and LIDAR Analyst Software
Outline of Presentation Automated Feature Extraction from Terrestrial and Airborne LIDAR Presented By: Stuart Blundell Overwatch Geospatial - VLS Ops Co-Author: David W. Opitz Overwatch Geospatial - VLS
More informationGeometric and Semantic 3D Reconstruction: Part 4A: Volumetric Semantic 3D Reconstruction. CVPR 2017 Tutorial Christian Häne UC Berkeley
Geometric and Semantic 3D Reconstruction: Part 4A: Volumetric Semantic 3D Reconstruction CVPR 2017 Tutorial Christian Häne UC Berkeley Dense Multi-View Reconstruction Goal: 3D Model from Images (Depth
More information3D Shape Analysis with Multi-view Convolutional Networks. Evangelos Kalogerakis
3D Shape Analysis with Multi-view Convolutional Networks Evangelos Kalogerakis 3D model repositories [3D Warehouse - video] 3D geometry acquisition [KinectFusion - video] 3D shapes come in various flavors
More informationDeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material
DeepIM: Deep Iterative Matching for 6D Pose Estimation - Supplementary Material Yi Li 1, Gu Wang 1, Xiangyang Ji 1, Yu Xiang 2, and Dieter Fox 2 1 Tsinghua University, BNRist 2 University of Washington
More informationObject Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning
Allan Zelener Dissertation Proposal December 12 th 2016 Object Localization, Segmentation, Classification, and Pose Estimation in 3D Images using Deep Learning Overview 1. Introduction to 3D Object Identification
More information3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.
3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction
More informationLearning from 3D Data
Learning from 3D Data Thomas Funkhouser Princeton University* * On sabbatical at Stanford and Google Disclaimer: I am talking about the work of these people Shuran Song Andy Zeng Fisher Yu Yinda Zhang
More informationREGISTRATION OF AIRBORNE LASER DATA TO SURFACES GENERATED BY PHOTOGRAMMETRIC MEANS. Y. Postolov, A. Krupnik, K. McIntosh
REGISTRATION OF AIRBORNE LASER DATA TO SURFACES GENERATED BY PHOTOGRAMMETRIC MEANS Y. Postolov, A. Krupnik, K. McIntosh Department of Civil Engineering, Technion Israel Institute of Technology, Haifa,
More informationSeeing the unseen. Data-driven 3D Understanding from Single Images. Hao Su
Seeing the unseen Data-driven 3D Understanding from Single Images Hao Su Image world Shape world 3D perception from a single image Monocular vision a typical prey a typical predator Cited from https://en.wikipedia.org/wiki/binocular_vision
More informationColored Point Cloud Registration Revisited Supplementary Material
Colored Point Cloud Registration Revisited Supplementary Material Jaesik Park Qian-Yi Zhou Vladlen Koltun Intel Labs A. RGB-D Image Alignment Section introduced a joint photometric and geometric objective
More information3D Deep Learning
3D Deep Learning Tutorial@CVPR2017 Hao Su (UCSD) Leonidas Guibas (Stanford) Michael Bronstein (Università della Svizzera Italiana) Evangelos Kalogerakis (UMass) Jimei Yang (Adobe Research) Charles Qi (Stanford)
More informationURBAN STRUCTURE ESTIMATION USING PARALLEL AND ORTHOGONAL LINES
URBAN STRUCTURE ESTIMATION USING PARALLEL AND ORTHOGONAL LINES An Undergraduate Research Scholars Thesis by RUI LIU Submitted to Honors and Undergraduate Research Texas A&M University in partial fulfillment
More informationRegion-based Segmentation and Object Detection
Region-based Segmentation and Object Detection Stephen Gould Tianshi Gao Daphne Koller Presented at NIPS 2009 Discussion and Slides by Eric Wang April 23, 2010 Outline Introduction Model Overview Model
More informationSeparating Objects and Clutter in Indoor Scenes
Separating Objects and Clutter in Indoor Scenes Salman H. Khan School of Computer Science & Software Engineering, The University of Western Australia Co-authors: Xuming He, Mohammed Bennamoun, Ferdous
More informationCell Decomposition for Building Model Generation at Different Scales
Cell Decomposition for Building Model Generation at Different Scales Norbert Haala, Susanne Becker, Martin Kada Institute for Photogrammetry Universität Stuttgart Germany forename.lastname@ifp.uni-stuttgart.de
More informationarxiv: v1 [cs.cv] 28 Sep 2018
Camera Pose Estimation from Sequence of Calibrated Images arxiv:1809.11066v1 [cs.cv] 28 Sep 2018 Jacek Komorowski 1 and Przemyslaw Rokita 2 1 Maria Curie-Sklodowska University, Institute of Computer Science,
More informationA Vision-based 2D-3D Registration System
A Vision-based 2D-3D Registration System Quan Wang, Suya You CGIT/IMSC USC Los Angeles, CA 90089 quanwang@usc.edu, suyay@graphics.usc.edu Abstract In this paper, we propose an automatic system for robust
More informationDEPT: Depth Estimation by Parameter Transfer for Single Still Images
DEPT: Depth Estimation by Parameter Transfer for Single Still Images Xiu Li 1, 2, Hongwei Qin 1,2, Yangang Wang 3, Yongbing Zhang 1,2, and Qionghai Dai 1 1. Dept. of Automation, Tsinghua University 2.
More informationBUILDING MODEL RECONSTRUCTION FROM DATA INTEGRATION INTRODUCTION
BUILDING MODEL RECONSTRUCTION FROM DATA INTEGRATION Ruijin Ma Department Of Civil Engineering Technology SUNY-Alfred Alfred, NY 14802 mar@alfredstate.edu ABSTRACT Building model reconstruction has been
More informationDescriptorEnsemble: An Unsupervised Approach to Image Matching and Alignment with Multiple Descriptors
DescriptorEnsemble: An Unsupervised Approach to Image Matching and Alignment with Multiple Descriptors 林彥宇副研究員 Yen-Yu Lin, Associate Research Fellow 中央研究院資訊科技創新研究中心 Research Center for IT Innovation, Academia
More informationRecovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform. Xintao Wang Ke Yu Chao Dong Chen Change Loy
Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform Xintao Wang Ke Yu Chao Dong Chen Change Loy Problem enlarge 4 times Low-resolution image High-resolution image Previous
More informationIllumination Estimation from Shadow Borders
Illumination Estimation from Shadow Borders Alexandros Panagopoulos, Tomás F. Yago Vicente, Dimitris Samaras Stony Brook University Stony Brook, NY, USA {apanagop, tyagovicente, samaras}@cs.stonybrook.edu
More informationPing Tan. Simon Fraser University
Ping Tan Simon Fraser University Photos vs. Videos (live photos) A good photo tells a story Stories are better told in videos Videos in the Mobile Era (mobile & share) More videos are captured by mobile
More informationSemantic Parsing of Street Scene Images Using 3D LiDAR Point Cloud
2013 IEEE International Conference on Computer Vision Workshops Semantic Parsing of Street Scene Images Using 3D LiDAR Point Cloud Pouria Babahajiani Tampere University of Technology Tampere, Finland pouria.babahajiani@tut.fi
More informationModeling Interactive Furniture from a Single Image
Modeling Interactive Furniture from a Single Image Bo Gao, Xiaowu Chen, Jianwei Li, Dongqing Zou State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering,
More informationAUTOMATED 3D MODELING OF URBAN ENVIRONMENTS
AUTOMATED 3D MODELING OF URBAN ENVIRONMENTS Ioannis Stamos Department of Computer Science Hunter College, City University of New York 695 Park Avenue, New York NY 10065 istamos@hunter.cuny.edu http://www.cs.hunter.cuny.edu/
More informationAutomated Extraction of Buildings from Aerial LiDAR Point Cloud and Digital Imaging Datasets for 3D Cadastre - Preliminary Results
Automated Extraction of Buildings from Aerial LiDAR Point Cloud and Digital Imaging Datasets for 3D Pankaj Kumar 1*, Alias Abdul Rahman 1 and Gurcan Buyuksalih 2 ¹Department of Geoinformation Universiti
More informationLearning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009
Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer
More informationFAST PRODUCTION OF VIRTUAL REALITY CITY MODELS
FAST PRODUCTION OF VIRTUAL REALITY CITY MODELS Claus Brenner and Norbert Haala Institute for Photogrammetry (ifp) University of Stuttgart Geschwister-Scholl-Straße 24, 70174 Stuttgart, Germany Ph.: +49-711-121-4097,
More informationFAST REGISTRATION OF TERRESTRIAL LIDAR POINT CLOUD AND SEQUENCE IMAGES
FAST REGISTRATION OF TERRESTRIAL LIDAR POINT CLOUD AND SEQUENCE IMAGES Jie Shao a, Wuming Zhang a, Yaqiao Zhu b, Aojie Shen a a State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing
More informationLarge Scale 3D Reconstruction (50 mins) Yasutaka Washington University in St. Louis
Large Scale 3D Reconstruction (50 mins) Yasutaka Furukawa @ Washington University in St. Louis Outline 1. Large scale MVS for organized photos (Aerial photos) 2. Large scale MVS for unorganized photos
More informationAutomatic Dense Semantic Mapping From Visual Street-level Imagery
Automatic Dense Semantic Mapping From Visual Street-level Imagery Sunando Sengupta [1], Paul Sturgess [1], Lubor Ladicky [2], Phillip H.S. Torr [1] [1] Oxford Brookes University [2] Visual Geometry Group,
More informationSIMPLE ROOM SHAPE MODELING WITH SPARSE 3D POINT INFORMATION USING PHOTOGRAMMETRY AND APPLICATION SOFTWARE
SIMPLE ROOM SHAPE MODELING WITH SPARSE 3D POINT INFORMATION USING PHOTOGRAMMETRY AND APPLICATION SOFTWARE S. Hirose R&D Center, TOPCON CORPORATION, 75-1, Hasunuma-cho, Itabashi-ku, Tokyo, Japan Commission
More informationBridging the Gap Between Local and Global Approaches for 3D Object Recognition. Isma Hadji G. N. DeSouza
Bridging the Gap Between Local and Global Approaches for 3D Object Recognition Isma Hadji G. N. DeSouza Outline Introduction Motivation Proposed Methods: 1. LEFT keypoint Detector 2. LGS Feature Descriptor
More informationFaçade Reconstruction An Interactive Image-Based Approach
Façade Reconstruction An Interactive Image-Based Approach Przemyslaw Musialski Institute of Computer Graphics and Algorithms Vienna University of Technology What is Façade Reconstruction? Part of Urban
More informationAUTOMATIC EXTRACTION OF BUILDING ROOFS FROM PICTOMETRY S ORTHOGONAL AND OBLIQUE IMAGES
AUTOMATIC EXTRACTION OF BUILDING ROOFS FROM PICTOMETRY S ORTHOGONAL AND OBLIQUE IMAGES Yandong Wang Pictometry International Corp. Suite A, 100 Town Centre Dr., Rochester, NY14623, the United States yandong.wang@pictometry.com
More informationAUTOMATIC EXTRACTION OF LARGE COMPLEX BUILDINGS USING LIDAR DATA AND DIGITAL MAPS
AUTOMATIC EXTRACTION OF LARGE COMPLEX BUILDINGS USING LIDAR DATA AND DIGITAL MAPS Jihye Park a, Impyeong Lee a, *, Yunsoo Choi a, Young Jin Lee b a Dept. of Geoinformatics, The University of Seoul, 90
More informationGeometry based Repetition Detection for Urban Scene
Geometry based Repetition Detection for Urban Scene Changchang Wu University of Washington Jan Michael Frahm UNC Chapel Hill Marc Pollefeys ETH Zürich Related Work Sparse Feature Matching [Loy et al. 06,
More informationIntrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting
Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting R. Maier 1,2, K. Kim 1, D. Cremers 2, J. Kautz 1, M. Nießner 2,3 Fusion Ours 1
More informationFitting boxes to Manhattan scenes using linear integer programming
Fitting boxes to Manhattan scenes using linear integer programming Item Type Article Authors Li, Minglei; Nan, Liangliang; Liu, Shaochuang Citation Fitting boxes to Manhattan scenes using linear integer
More informationGRAMMAR SUPPORTED FACADE RECONSTRUCTION FROM MOBILE LIDAR MAPPING
GRAMMAR SUPPORTED FACADE RECONSTRUCTION FROM MOBILE LIDAR MAPPING Susanne Becker, Norbert Haala Institute for Photogrammetry, University of Stuttgart Geschwister-Scholl-Straße 24D, D-70174 Stuttgart forename.lastname@ifp.uni-stuttgart.de
More informationBuilding Reliable 2D Maps from 3D Features
Building Reliable 2D Maps from 3D Features Dipl. Technoinform. Jens Wettach, Prof. Dr. rer. nat. Karsten Berns TU Kaiserslautern; Robotics Research Lab 1, Geb. 48; Gottlieb-Daimler- Str.1; 67663 Kaiserslautern;
More informationSpeaker: Ming-Ming Cheng Nankai University 15-Sep-17 Towards Weakly Supervised Image Understanding
Towards Weakly Supervised Image Understanding (WSIU) Speaker: Ming-Ming Cheng Nankai University http://mmcheng.net/ 1/50 Understanding Visual Information Image by kirkh.deviantart.com 2/50 Dataset Annotation
More informationSurface reconstruction Introduction. Florent Lafarge Inria Sophia Antipolis - Mediterranee
Surface reconstruction Introduction Florent Lafarge Inria Sophia Antipolis - Mediterranee Outline Contents Introduction Smooth/piecewise-smooth reconstruction methods Primitive-based reconstruction methods
More informationDiscrete Optimization of Ray Potentials for Semantic 3D Reconstruction
Discrete Optimization of Ray Potentials for Semantic 3D Reconstruction Marc Pollefeys Joined work with Nikolay Savinov, Christian Haene, Lubor Ladicky 2 Comparison to Volumetric Fusion Higher-order ray
More informationAdvanced point cloud processing
Advanced point cloud processing George Vosselman ITC Enschede, the Netherlands INTERNATIONAL INSTITUTE FOR GEO-INFORMATION SCIENCE AND EARTH OBSERVATION Laser scanning platforms Airborne systems mounted
More informationREPORT DOCUMENTATION PAGE
REPORT DOCUMENTATION PAGE Form Approved OMB NO. 0704-0188 The public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions,
More informationHEURISTIC FILTERING AND 3D FEATURE EXTRACTION FROM LIDAR DATA
HEURISTIC FILTERING AND 3D FEATURE EXTRACTION FROM LIDAR DATA Abdullatif Alharthy, James Bethel School of Civil Engineering, Purdue University, 1284 Civil Engineering Building, West Lafayette, IN 47907
More informationAUTOMATIC 3D BUILDING RECONSTRUCTION FROM DEMS : AN APPLICATION TO PLEIADES SIMULATIONS
AUTOMATIC 3D BUILDING RECONSTRUCTION FROM DEMS : AN APPLICATION TO PLEIADES SIMULATIONS Florent Lafarge 1,2, Xavier Descombes 1, Josiane Zerubia 1 and Marc Pierrot-Deseilligny 2 1 Ariana Research Group
More informationPredicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus Presented by: Rex Ying and Charles Qi Input: A Single RGB Image Estimate
More informationSingle Image Super-resolution. Slides from Libin Geoffrey Sun and James Hays
Single Image Super-resolution Slides from Libin Geoffrey Sun and James Hays Cs129 Computational Photography James Hays, Brown, fall 2012 Types of Super-resolution Multi-image (sub-pixel registration) Single-image
More informationModeling and Analyzing 3D Shapes using Clues from 2D Images. Minglun Gong Dept. of CS, Memorial Univ.
Modeling and Analyzing 3D Shapes using Clues from 2D Images Minglun Gong Dept. of CS, Memorial Univ. Modeling Flowers from Images Reconstructing 3D flower petal shapes from a single image is difficult
More informationTriangular Mesh Segmentation Based On Surface Normal
ACCV2002: The 5th Asian Conference on Computer Vision, 23--25 January 2002, Melbourne, Australia. Triangular Mesh Segmentation Based On Surface Normal Dong Hwan Kim School of Electrical Eng. Seoul Nat
More informationCost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling
[DOI: 10.2197/ipsjtcva.7.99] Express Paper Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling Takayoshi Yamashita 1,a) Takaya Nakamura 1 Hiroshi Fukui 1,b) Yuji
More informationMulti-ray photogrammetry: A rich dataset for the extraction of roof geometry for 3D reconstruction
Multi-ray photogrammetry: A rich dataset for the extraction of roof geometry for 3D reconstruction Andrew McClune, Pauline Miller, Jon Mills Newcastle University David Holland Ordnance Survey Background
More informationLearning based face hallucination techniques: A survey
Vol. 3 (2014-15) pp. 37-45. : A survey Premitha Premnath K Department of Computer Science & Engineering Vidya Academy of Science & Technology Thrissur - 680501, Kerala, India (email: premithakpnath@gmail.com)
More informationAUTOMATED RECONSTRUCTION OF WALLS FROM AIRBORNE LIDAR DATA FOR COMPLETE 3D BUILDING MODELLING
AUTOMATED RECONSTRUCTION OF WALLS FROM AIRBORNE LIDAR DATA FOR COMPLETE 3D BUILDING MODELLING Yuxiang He*, Chunsun Zhang, Mohammad Awrangjeb, Clive S. Fraser Cooperative Research Centre for Spatial Information,
More informationCRF Based Point Cloud Segmentation Jonathan Nation
CRF Based Point Cloud Segmentation Jonathan Nation jsnation@stanford.edu 1. INTRODUCTION The goal of the project is to use the recently proposed fully connected conditional random field (CRF) model to
More informationAutomated Processing for 3D Mosaic Generation, a Change of Paradigm
Automated Processing for 3D Mosaic Generation, a Change of Paradigm Frank BIGNONE, Japan Key Words: 3D Urban Model, Street Imagery, Oblique imagery, Mobile Mapping System, Parallel processing, Digital
More informationEstimating Human Pose in Images. Navraj Singh December 11, 2009
Estimating Human Pose in Images Navraj Singh December 11, 2009 Introduction This project attempts to improve the performance of an existing method of estimating the pose of humans in still images. Tasks
More informationLearning Deep Structured Models for Semantic Segmentation. Guosheng Lin
Learning Deep Structured Models for Semantic Segmentation Guosheng Lin Semantic Segmentation Outline Exploring Context with Deep Structured Models Guosheng Lin, Chunhua Shen, Ian Reid, Anton van dan Hengel;
More informationEstimation of Camera Pose with Respect to Terrestrial LiDAR Data
Estimation of Camera Pose with Respect to Terrestrial LiDAR Data Wei Guan Suya You Guan Pang Computer Science Department University of Southern California, Los Angeles, USA Abstract In this paper, we present
More informationFACADE SEGMENTATION WITH A STRUCTURED RANDOM FOREST
FACADE SEGMENTATION WITH A STRUCTURED RANDOM FOREST Kujtim Rahmani, Hai Huang, Helmut Mayer Bundeswehr University Munich, Institute for Applied Computer Science, Visual Computing, Neubiberg, Germany {kujtim.rahmani,
More informationI. INTRODUCTION. Figure-1 Basic block of text analysis
ISSN: 2349-7637 (Online) (RHIMRJ) Research Paper Available online at: www.rhimrj.com Detection and Localization of Texts from Natural Scene Images: A Hybrid Approach Priyanka Muchhadiya Post Graduate Fellow,
More informationDEPT: Depth Estimation by Parameter Transfer for Single Still Images
DEPT: Depth Estimation by Parameter Transfer for Single Still Images Xiu Li 1,2, Hongwei Qin 1,2(B), Yangang Wang 3, Yongbing Zhang 1,2, and Qionghai Dai 1 1 Department of Automation, Tsinghua University,
More informationIdentifying man-made objects along urban road corridors from mobile LiDAR data
Identifying man-made objects along urban road corridors from mobile LiDAR data Hongchao Fan 1 and Wei Yao 2 1 Chair of GIScience, Heidelberg University, Berlinerstr. 48, 69120 Heidelberg, Hongchao.fan@geog.uni-heidelberg.de
More informationA New Smoothing Algorithm for Quadrilateral and Hexahedral Meshes
A New Smoothing Algorithm for Quadrilateral and Hexahedral Meshes Sanjay Kumar Khattri Department of Mathematics, University of Bergen, Norway sanjay@mi.uib.no http://www.mi.uib.no/ sanjay Abstract. Mesh
More informationLatent Variable Models for Structured Prediction and Content-Based Retrieval
Latent Variable Models for Structured Prediction and Content-Based Retrieval Ariadna Quattoni Universitat Politècnica de Catalunya Joint work with Borja Balle, Xavier Carreras, Adrià Recasens, Antonio
More informationA Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation
, pp.162-167 http://dx.doi.org/10.14257/astl.2016.138.33 A Novel Image Super-resolution Reconstruction Algorithm based on Modified Sparse Representation Liqiang Hu, Chaofeng He Shijiazhuang Tiedao University,
More informationDetection and Fine 3D Pose Estimation of Texture-less Objects in RGB-D Images
Detection and Pose Estimation of Texture-less Objects in RGB-D Images Tomáš Hodaň1, Xenophon Zabulis2, Manolis Lourakis2, Šťěpán Obdržálek1, Jiří Matas1 1 Center for Machine Perception, CTU in Prague,
More informationSemi-Automatic Techniques for Generating BIM Façade Models of Historic Buildings
Semi-Automatic Techniques for Generating BIM Façade Models of Historic Buildings C. Dore, M. Murphy School of Surveying & Construction Management Dublin Institute of Technology Bolton Street Campus, Dublin
More informationPerceiving the 3D World from Images and Videos. Yu Xiang Postdoctoral Researcher University of Washington
Perceiving the 3D World from Images and Videos Yu Xiang Postdoctoral Researcher University of Washington 1 2 Act in the 3D World Sensing & Understanding Acting Intelligent System 3D World 3 Understand
More information3D Models from Range Sensors. Gianpaolo Palma
3D Models from Range Sensors Gianpaolo Palma Who Gianpaolo Palma Researcher at Visual Computing Laboratory (ISTI-CNR) Expertise: 3D scanning, Mesh Processing, Computer Graphics E-mail: gianpaolo.palma@isti.cnr.it
More informationLow-Rank Based Algorithms for Rectification, Repetition Detection and De-Noising in Urban Images. A dissertation proposal by Juan Liu
Low-Rank Based Algorithms for Rectification, Repetition Detection and De-Noising in Urban Images A dissertation proposal by Juan Liu Committee Committee: Professor Ioannis Stamos, Mentor, Hunter College
More informationAN AUTOMATIC 3D RECONSTRUCTION METHOD BASED ON MULTI-VIEW STEREO VISION FOR THE MOGAO GROTTOES
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XL-4/W5, 05 Indoor-Outdoor Seamless Modelling, Mapping and avigation, May 05, Tokyo, Japan A AUTOMATIC
More informationTextured Mesh Surface Reconstruction of Large Buildings with Multi-View Stereo
The Visual Computer manuscript No. (will be inserted by the editor) Textured Mesh Surface Reconstruction of Large Buildings with Multi-View Stereo Chen Zhu Wee Kheng Leow Received: date / Accepted: date
More informationCLASSIFICATION FOR ROADSIDE OBJECTS BASED ON SIMULATED LASER SCANNING
CLASSIFICATION FOR ROADSIDE OBJECTS BASED ON SIMULATED LASER SCANNING Kenta Fukano 1, and Hiroshi Masuda 2 1) Graduate student, Department of Intelligence Mechanical Engineering, The University of Electro-Communications,
More informationFace Recognition At-a-Distance Based on Sparse-Stereo Reconstruction
Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction Ham Rara, Shireen Elhabian, Asem Ali University of Louisville Louisville, KY {hmrara01,syelha01,amali003}@louisville.edu Mike Miller,
More informationcoding of various parts showing different features, the possibility of rotation or of hiding covering parts of the object's surface to gain an insight
Three-Dimensional Object Reconstruction from Layered Spatial Data Michael Dangl and Robert Sablatnig Vienna University of Technology, Institute of Computer Aided Automation, Pattern Recognition and Image
More informationSemantic Segmentation of Street-Side Images
Semantic Segmentation of Street-Side Images Michal Recky 1, Franz Leberl 2 1 Institute for Computer Graphics and Vision Graz University of Technology recky@icg.tugraz.at 2 Institute for Computer Graphics
More informationGraph-based Modeling of Building Roofs Judith Milde, Claus Brenner Institute of Cartography and Geoinformatics, Leibniz Universität Hannover
12th AGILE International Conference on Geographic Information Science 2009 page 1 of 5 Graph-based Modeling of Building Roofs Judith Milde, Claus Brenner Institute of Cartography and Geoinformatics, Leibniz
More information