Sponsored by Deformation-Driven Topology-Varying 3D Shape Correspondence Ibraheem Alhashim Kai Xu Yixin Zhuang Junjie Cao Patricio Simari Hao Zhang Presenter:

Slides:



Advertisements
Similar presentations
Complexity Metrics for Design & Manufacturability Analysis
Advertisements

1/50 Photo-Inspired Model-Driven 3D Object Modeling Kai Xu 1,2 Hanlin Zheng 3 Hao (Richard) Zhang 2 Daniel Cohen-Or 4 Ligang Liu 3 Yueshan Xiong 1 1 National.
A Search-Classify Approach for Cluttered Indoor Scene Understanding Liangliang Nan 1, Ke Xie 1, Andrei Sharf 2 1 SIAT, China 2 Ben Gurion University, Israel.
GRAPP, Lisbon, February 2009 University of Ioannina Skeleton-based Rigid Skinning for Character Animation Andreas Vasilakis and Ioannis Fudos Department.
Junjie Cao 1, Andrea Tagliasacchi 2, Matt Olson 2, Hao Zhang 2, Zhixun Su 1 1 Dalian University of Technology 2 Simon Fraser University Point Cloud Skeletons.
Creating Consistent Scene Graphs Using a Probabilistic Grammar Tianqiang LiuSiddhartha ChaudhuriVladimir G. Kim Qi-Xing HuangNiloy J. MitraThomas Funkhouser.
SPONSORED BY SA2014.SIGGRAPH.ORG Annotating RGBD Images of Indoor Scenes Yu-Shiang Wong and Hung-Kuo Chu National Tsing Hua University CGV LAB.
SPONSORED BY SA2014.SIGGRAPH.ORG MCGraph: Multi-criterion representation for scene understanding Moos Hueting ∗ Aron Monszpart ∗ Nicolas Mellado University.
Extended Gaussian Images
International Conference on Automatic Face and Gesture Recognition, 2006 A Layered Deformable Model for Gait Analysis Haiping Lu, K.N. Plataniotis and.
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
Creating Consistent Scene Graphs Using a Probabilistic Grammar Tianqiang LiuSiddhartha ChaudhuriVladimir G. Kim Qi-Xing HuangNiloy J. MitraThomas Funkhouser.
Structure Recovery by Part Assembly Chao-Hui Shen 1 Hongbo Fu 2 Kang Chen 1 Shi-Min Hu 1 1 Tsinghua University 2 City University of Hong Kong.
Modeling 3D Deformable and Articulated Shapes Yu Chen, Tae-Kyun Kim, Roberto Cipolla Department of Engineering University of Cambridge.
Shape Classification Alex Yakubovich Elderlab Oct 7, 2011 John Wilder, Jacob Feldman, Manish Singh, Superordinate shape classification using natural shape.
Inter-Surface Mapping John Schreiner, Arul Asirvatham, Emil Praun (University of Utah) Hugues Hoppe (Microsoft Research)
3D Skeletons Using Graphics Hardware Jonathan Bilodeau Chris Niski.
Model-Driven 3D Content Creation as Variation Hao (Richard) Zhang – 张皓 GrUVi Lab, Simon Fraser University (SFU) HKUST, 04/21/11 TAUZJUNUDT SFU.
An Optimization Approach to Improving Collections of Shape Maps Andy Nguyen, Mirela Ben-Chen, Katarzyna Welnicka, Yinyu Ye, Leonidas Guibas Computer Science.
GATE D Object Representations (GATE-540) Dr.Çağatay ÜNDEĞER Instructor Middle East Technical University, GameTechnologies & General Manager SimBT.
Motion Detail Preserving Optical Flow Estimation Li Xu 1, Jiaya Jia 1, Yasuyuki Matsushita 2 1 The Chinese University of Hong Kong 2 Microsoft Research.
Learning 3D mesh segmentation and labeling Evangelos Kalogerakis, Aaron Hertzmann, Karan Singh University of Toronto Head Tors o Upper arm Lower arm Hand.
Tinghui Zhou1, Yong Jae Lee2, Stella X. Yu1,3, Alexei A. Efros1
Prior Knowledge for Part Correspondence Oliver van Kaick 1, Andrea Tagliasacchi 1, Oana Sidi 2, Hao Zhang 1, Daniel Cohen-Or 2, Lior Wolf 2, Ghassan Hamarneh.
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Efficient Algorithms for Matching Pedro Felzenszwalb Trevor Darrell Yann LeCun Alex Berg.
Symmetry Hierarchy of Man-Made Objects Yanzhen Wang 1,2, Kai Xu 1,2, Jun Li 2, Hao Zhang 1, Ariel Shamir 3, Ligang Liu 4, Zhiquan Cheng 2, Yueshan Xiong.
Context-based Surface Completion Andrei Sharf, Marc Alexa, Daniel Cohen-Or.
 An important problem in sponsored search advertising is keyword generation, which bridges the gap between the keywords bidded by advertisers and queried.
Shape Matching for Model Alignment 3D Scan Matching and Registration, Part I ICCV 2005 Short Course Michael Kazhdan Johns Hopkins University.
1 Style-Content Separation by Anisotropic Part Scales Kai Xu, Honghua Li, Hao Zhang, Daniel Cohen-Or Yueshan Xiong, Zhi-Quan Cheng Simon Fraser Universtiy.
Interactive Discovery and Semantic Labeling of Patterns in Spatial Data Thomas Funkhouser, Adam Finkelstein, David Blei, and Christiane Fellbaum Princeton.
SPONSORED BY Data-driven Segmentation and Labeling of Freehand Sketches Zhe Huang, Hongbo Fu, Rynson W.H. Lau City University of Hong Kong.
Shape Analysis and Retrieval Structural Shape Descriptors Notes courtesy of Funk et al., SIGGRAPH 2004.
Organizing Heterogeneous Scene Collections through Contextual Focal Points Kai Xu, Rui Ma, Hao Zhang, Chenyang Zhu, Ariel Shamir, Daniel Cohen-Or, Hui.
TEMPLATE DESIGN © Zhiyao Duan 1,2, Lie Lu 1, and Changshui Zhang 2 1. Microsoft Research Asia (MSRA), Beijing, China.2.
5. SUMMARY & CONCLUSIONS We have presented a coarse to fine minimization framework using a coupled dual ellipse model to form a subspace constraint that.
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
A survey of different shape analysis techniques 1 A Survey of Different Shape Analysis Techniques -- Huang Nan.
Extraction and remeshing of ellipsoidal representations from mesh data Patricio Simari Karan Singh.
Acquiring 3D Indoor Environments with Variability and Repetition Young Min Kim Stanford University Niloy J. Mitra UCL/ KAUST Dong-Ming Yan KAUST Leonidas.
Temporally Coherent Completion of Dynamic Shapes AUTHORS:HAO LI,LINJIE LUO,DANIEL VLASIC PIETER PEERS,JOVAN POPOVIC,MARK PAULY,SZYMON RUSINKIEWICZ Presenter:Zoomin(Zhuming)
Course: Structure-Aware Shape Processing Hao (Richard) Zhang Simon Fraser University (SFU), Canada Structural Hierarchies Course: Structure-Aware Shape.
1 Minimum Error Rate Training in Statistical Machine Translation Franz Josef Och Information Sciences Institute University of Southern California ACL 2003.
Methods for 3D Shape Matching and Retrieval
Semi-supervised Mesh Segmentation and Labeling
SA2014.SIGGRAPH.ORG SPONSORED BY Automatic Semantic Modeling of Indoor Scenes from Low-quality RGB-D Data using Contextual Information Kang Chen 1 Yu-Kun.
Linear Solution to Scale and Rotation Invariant Object Matching Hao Jiang and Stella X. Yu Computer Science Department Boston College.
Stackabilization Honghua Li, Ibraheem Alhashim, Hao Zhang, Ariel Shamir, Daniel Cohen-Or.
Course: Structure-Aware Shape Processing Introduction to Geometric ‘Structure’ Extracting Structures –analysis of Individual Models –analysis of Shape.
Feature-sensitive 3D Shape Matching Andrei Sharf Tel-Aviv University Ariel Shamir IDC Hertzliya.
Course: Structure-Aware Shape Processing Introduction to Geometric ‘Structure’ Extracting Structures –analysis of Individual Models –analysis of Shape.
1 Double-Patterning Aware DSA Template Guided Cut Redistribution for Advanced 1-D Gridded Designs Zhi-Wen Lin and Yao-Wen Chang National Taiwan University.
Shape2Pose: Human Centric Shape Analysis CMPT888 Vladimir G. Kim Siddhartha Chaudhuri Leonidas Guibas Thomas Funkhouser Stanford University Princeton University.
Co-Hierarchical Analysis of Shape Structures Oliver van Kaick 1,4 Kai Xu 2 Hao Zhang 1 Yanzhen Wang 2 Shuyang Sun 1 Ariel Shamir 3 Daniel Cohen-Or 4 4.
Prior Knowledge for Part Correspondence
Physical Structure of GDB
Motivation Skeleton needed for mesh deformation:
Adversarial Learning for Neural Dialogue Generation
Morphing and Shape Processing
Nonparametric Semantic Segmentation
Cold-Start Heterogeneous-Device Wireless Localization
Dynamical Statistical Shape Priors for Level Set Based Tracking
Local Feature Extraction Using Scale-Space Decomposition
Efficient Graph Cut Optimization for Full CRFs with Quantized Edges
Scale-Space Representation of 3D Models and Topological Matching
CSc4730/6730 Scientific Visualization
Topology-Varying 3D Shape Creation via Structural Blending
Scale-Space Representation for Matching of 3D Models
Autonomously designed free-form 2D DNA origami
Presentation transcript:

Sponsored by Deformation-Driven Topology-Varying 3D Shape Correspondence Ibraheem Alhashim Kai Xu Yixin Zhuang Junjie Cao Patricio Simari Hao Zhang Presenter: Ibraheem Alhashim Simon Fraser University

SA2015.SIGGRAPH.ORG 2 Deformation-Driven Topology-Varying 3D Shape Correspondence Shape Correspondence Fundamental task in: Shape morphing Statistical shape modeling Object recognition Classification

SA2015.SIGGRAPH.ORG 3 Deformation-Driven Topology-Varying 3D Shape Correspondence Shape Correspondence Corresponding man-made 3D shapes is challenging Large variability in geometry & structure Real-world data is inconsistent & unlabeled

SA2015.SIGGRAPH.ORG 4 Deformation-Driven Topology-Varying 3D Shape Correspondence Shape Correspondence Part-level correspondences [Jain 12] [Xu 12] [Zheng 13] [Averkiou 14] [Kalogerakis 12]

SA2015.SIGGRAPH.ORG 5 Deformation-Driven Topology-Varying 3D Shape Correspondence Shape Correspondence Continuous fine-grained correspondence is critical for continuous shape blending [Alhashim et al. 14]

SA2015.SIGGRAPH.ORG 6 Deformation-Driven Topology-Varying 3D Shape Correspondence Previous Works Rigid alignment not sufficient for diverse shapes [Golovinskiy & Funkhouser 08]

SA2015.SIGGRAPH.ORG 7 Deformation-Driven Topology-Varying 3D Shape Correspondence Previous Works [Zheng et al. 14] [Kim et al. 13] [Laga et al. 14] [Huang et al. 14] Co-analysis methods Coarse results Forced correspondence Set of shapes

SA2015.SIGGRAPH.ORG 8 Deformation-Driven Topology-Varying 3D Shape Correspondence Deformation-Driven Shape Matching Best matching = minimal self- distortion as we deform one shape to match the other [Zhang et al. 08] [Sederberg & Greenwood 92]

SA2015.SIGGRAPH.ORG 9 Deformation-Driven Topology-Varying 3D Shape Correspondence Challenge How to apply a deformation-driven search to complex man-made shapes? Many disconnected components Semantically similar yet very different Discrepancy in part count & structural relations Back Seat Legs

SA2015.SIGGRAPH.ORG 10 Deformation-Driven Topology-Varying 3D Shape Correspondence Our Proposal The GeoTopo transform Piece-wise continuous part correspondence Supports topological changes No prior or fixed number of segments Efficient to compute Works on pairs

SA2015.SIGGRAPH.ORG 11 Deformation-Driven Topology-Varying 3D Shape Correspondence Our Proposal The GeoTopo transform Deformation model Distortion Energy

SA2015.SIGGRAPH.ORG 12 Deformation-Driven Topology-Varying 3D Shape Correspondence Deformation Model Deformation suitable for man-made shapes Supports disconnected components Structure-aware (preserving part relations) Allows for topological changes

SA2015.SIGGRAPH.ORG 13 Deformation-Driven Topology-Varying 3D Shape Correspondence Self-Distortion Energy Structural distortion in three terms: 1.Distortion on all pairs of connected parts 2.Connectivity between parts 3.Solidity measure for parts changing topology

SA2015.SIGGRAPH.ORG 14 Deformation-Driven Topology-Varying 3D Shape Correspondence Shape Representation A structure graph of part skeletons [Alhashim et al. 2014] Skeletons are fitted by parametric curves / sheets Parametric curves Parametri c sheet

SA2015.SIGGRAPH.ORG 15 Deformation-Driven Topology-Varying 3D Shape Correspondence Structural Rods 3D shapeCurve-sheet abstractions Structural rods

SA2015.SIGGRAPH.ORG 16 Deformation-Driven Topology-Varying 3D Shape Correspondence Energy Distortion term E d – Overall change of part arrangements – Change in angle

SA2015.SIGGRAPH.ORG 17 Deformation-Driven Topology-Varying 3D Shape Correspondence Energy Distortion term E d Best correspondence Before deformation After deformation

SA2015.SIGGRAPH.ORG 18 Deformation-Driven Topology-Varying 3D Shape Correspondence Energy Connectivity term E c – Relative length of shortest rods before and after deformation Source shapeDeformed shapeTarget

SA2015.SIGGRAPH.ORG 19 Deformation-Driven Topology-Varying 3D Shape Correspondence Energy Solidity term E s – Ratio between the volume of a part to the volume of its convex hull – Measures the effect of a split / merge High Low High

SA2015.SIGGRAPH.ORG 20 Deformation-Driven Topology-Varying 3D Shape Correspondence Energy Solidity term E s ? ?

SA2015.SIGGRAPH.ORG 21 Deformation-Driven Topology-Varying 3D Shape Correspondence Deformation Process Deform-to-fit matched parts, then propagate Curves Sheets 1. Align centers 2. Match extremities 3. Deform towards target 4. Propagate edit to others

SA2015.SIGGRAPH.ORG 22 Deformation-Driven Topology-Varying 3D Shape Correspondence Search Search tree path: set of matched parts on the source Beam search + pruning 3D shapesCurve-sheet abstractions seat-seat back bar- back bar back-back leg back- leg back leg front- leg front

SA2015.SIGGRAPH.ORG 23 Deformation-Driven Topology-Varying 3D Shape Correspondence Results

SA2015.SIGGRAPH.ORG 24 Deformation-Driven Topology-Varying 3D Shape Correspondence Results

SA2015.SIGGRAPH.ORG 25 Deformation-Driven Topology-Varying 3D Shape Correspondence Applications Shape blending fully automatically!

SA2015.SIGGRAPH.ORG 26 Deformation-Driven Topology-Varying 3D Shape Correspondence Applications Topological medoidShape Classification

SA2015.SIGGRAPH.ORG 27 Deformation-Driven Topology-Varying 3D Shape Correspondence Evaluation Ground truth 75 shapes, 5 categories (chair, airplane, table, bed, velocipede) Fine and coarse labels

SA2015.SIGGRAPH.ORG 28 Deformation-Driven Topology-Varying 3D Shape Correspondence Evaluation [Xu 12] Fuzzy part correspondence (baseline) Works on pairs Match based on part OBB similarity [Zheng 14] Recurring part arrangements Find semantic consistency between part arrangements Performs better than co-segmentation in the presence of large shape variability [Kim 13] Deformable part-based templates Better suited for large shape sets Supports poorly segmented inputs + can be fully auto.

SA2015.SIGGRAPH.ORG 29 Deformation-Driven Topology-Varying 3D Shape Correspondence Evaluation Fine-grained correspondence benchmark

SA2015.SIGGRAPH.ORG 30 Deformation-Driven Topology-Varying 3D Shape Correspondence Evaluation Coarse correspondence benchmark (co- analysis)

SA2015.SIGGRAPH.ORG 31 Deformation-Driven Topology-Varying 3D Shape Correspondence Summary GeoTopo: topology-varying deformation model for a fine-grained correspondence search Key contribution: a deformation model and a self-distortion energy, defined on structural rods, assess shape matching quality based on preservation of structure Our framework shows promising results on challenging datasets with much room for improvement

SA2015.SIGGRAPH.ORG 32 Deformation-Driven Topology-Varying 3D Shape Correspondence Limitations Initial segmentation Large geo. and topo. differences

SA2015.SIGGRAPH.ORG 33 Deformation-Driven Topology-Varying 3D Shape Correspondence Future Work Segmentation Online shape repositories are not well segmented Incorporate a segmentation search along with the correspondence search High energyLow energy segmentation

SA2015.SIGGRAPH.ORG 34 Deformation-Driven Topology-Varying 3D Shape Correspondence Future Work Co-analysis Fine-grained correspondence on a set Looking for consistent assignments

SA2015.SIGGRAPH.ORG Sponsored by THANK YOU! gruvi.cs.sfu.ca/project/geotopo ACKNOWLEDGMENTS Anonymous reviewers, authors who provided code, funding from: NSFC

SA2015.SIGGRAPH.ORG 36 Deformation-Driven Topology-Varying 3D Shape Correspondence Partial Matching

SA2015.SIGGRAPH.ORG 37 Deformation-Driven Topology-Varying 3D Shape Correspondence Energy Terms

SA2015.SIGGRAPH.ORG 38 Deformation-Driven Topology-Varying 3D Shape Correspondence Automatic Segmentation SDFCon. AwareConvex. Analysis Approximate Convexity Analysis

SA2015.SIGGRAPH.ORG 39 Deformation-Driven Topology-Varying 3D Shape Correspondence Cost & Quality Trade-off

SA2015.SIGGRAPH.ORG 40 Deformation-Driven Topology-Varying 3D Shape Correspondence Timing & Shapes Complexity

Topology-Varying Shape Matching and Modeling Structure Preservation Edit propagation – Reinforce symmetry and contact relations 41