Partial and Approximate Symmetry Detection for 3D Geometry Mark Pauly Niloy J. Mitra Leonidas J. Guibas.

Slides:



Advertisements
Similar presentations
Distinctive Image Features from Scale-Invariant Keypoints David Lowe.
Advertisements

Image Registration  Mapping of Evolution. Registration Goals Assume the correspondences are known Find such f() and g() such that the images are best.
BRIEF: Binary Robust Independent Elementary Features
Robust Global Registration Natasha Gelfand Niloy Mitra Leonidas Guibas Helmut Pottmann.
Kernel-based tracking and video patch replacement Igor Guskov
Computer Vision Detecting the existence, pose and position of known objects within an image Michael Horne, Philip Sterne (Supervisor)
Amir Hosein Omidvarnia Spring 2007 Principles of 3D Face Recognition.
Probabilistic Fingerprints for Shapes Niloy J. MitraLeonidas Guibas Joachim GiesenMark Pauly Stanford University MPII SaarbrückenETH Zurich.
Instructor: Mircea Nicolescu Lecture 13 CS 485 / 685 Computer Vision.
Semi-automatic Range to Range Registration: A Feature-based Method Chao Chen & Ioannis Stamos Computer Science Department Graduate Center, Hunter College.
Reverse Engineering Niloy J. Mitra.
Robust and large-scale alignment Image from
Example Based 3D Shape Completion Mark Pauly 1,2, Niloy J. Mitra 1, Joachim Giesen 2, Markus Gross 2, Leonidas J. Guibas 1 1 Stanford University 2 ETH,
Final Class: Range Data registration CISC4/689 Credits: Tel-Aviv University.
Uncertainty and Variability in Point Cloud Surface Data Mark Pauly 1,2, Niloy J. Mitra 1, Leonidas J. Guibas 1 1 Stanford University 2 ETH, Zurich.
Iterative closest point algorithms
A Study of Approaches for Object Recognition
Correspondence & Symmetry
1 Numerical geometry of non-rigid shapes Spectral Methods Tutorial. Spectral Methods Tutorial 6 © Maks Ovsjanikov tosca.cs.technion.ac.il/book Numerical.
Randomized Cuts for 3D Mesh Analysis
Niloy J. Mitra1, Natasha Gelfand1, Helmut Pottmann2, Leonidas J
Stepan Obdrzalek Jirı Matas
Matching and Recognition in 3D. Moving from 2D to 3D Some things harderSome things harder – Rigid transform has 6 degrees of freedom vs. 3 – No natural.
Object Recognition Using Distinctive Image Feature From Scale-Invariant Key point D. Lowe, IJCV 2004 Presenting – Anat Kaspi.
1 Bronstein, Bronstein, and Kimmel Joint extrinsic and intrinsic similarity of non-rigid shapes Rock, paper, and scissors Joint extrinsic and intrinsic.
Scale Invariant Feature Transform (SIFT)
Multiple View Geometry Marc Pollefeys University of North Carolina at Chapel Hill Modified by Philippos Mordohai.
Spectral Processing of Point-sampled Geometry
3D full object reconstruction from kinect Yoni Choukroun Elie Semmel Advisor: Yonathan Afflalo.
The Planar-Reflective Symmetry Transform Princeton University.
A Hierarchical Method for Aligning Warped Meshes Leslie Ikemoto 1, Natasha Gelfand 2, Marc Levoy 2 1 UC Berkeley, formerly Stanford 2 Stanford University.
Robust Statistical Estimation of Curvature on Discretized Surfaces Evangelos Kalogerakis Patricio Simari Derek Nowrouzezahrai Karan Singh Symposium on.
Gender and 3D Facial Symmetry: What’s the Relationship ? Xia BAIQIANG (University Lille1/LIFL) Boulbaba Ben Amor (TELECOM Lille1/LIFL) Hassen Drira (TELECOM.
Gwangju Institute of Science and Technology Intelligent Design and Graphics Laboratory Multi-scale tensor voting for feature extraction from unstructured.
Context-based Surface Completion Andrei Sharf, Marc Alexa, Daniel Cohen-Or.
Niloy J. Mitra Leonidas J. Guibas Mark Pauly TU Vienna Stanford University ETH Zurich SIGGRAPH 2007.
Recognition and Matching based on local invariant features Cordelia Schmid INRIA, Grenoble David Lowe Univ. of British Columbia.
Shape Matching for Model Alignment 3D Scan Matching and Registration, Part I ICCV 2005 Short Course Michael Kazhdan Johns Hopkins University.
Local invariant features Cordelia Schmid INRIA, Grenoble.
Randomized Algorithms for Comparing and Understanding 3D Geometry Niloy J. Mitra Department of Electrical Engineering Advisor: Leonidas J. Guibas Associate.
ALIGNMENT OF 3D ARTICULATE SHAPES. Articulated registration Input: Two or more 3d point clouds (possibly with connectivity information) of an articulated.
A Method for Registration of 3D Surfaces ICP Algorithm
CSCE 643 Computer Vision: Structure from Motion
INFORMATIK Laplacian Surface Editing Olga Sorkine Daniel Cohen-Or Yaron Lipman Tel Aviv University Marc Alexa TU Darmstadt Christian Rössl Hans-Peter Seidel.
Features-based Object Recognition P. Moreels, P. Perona California Institute of Technology.
Local invariant features Cordelia Schmid INRIA, Grenoble.
Adaptive Rigid Multi-region Selection for 3D face recognition K. Chang, K. Bowyer, P. Flynn Paper presentation Kin-chung (Ryan) Wong 2006/7/27.
Efficient Raytracing of Deforming Point-Sampled Surfaces Mark Pauly Leonidas J. Guibas Bart Adams Philip Dutré Richard Keiser Markus Gross.
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)
EFFICIENT VARIANTS OF THE ICP ALGORITHM
The Planar-Reflective Symmetry Transform Princeton University.
CSE 185 Introduction to Computer Vision Feature Matching.
Distinctive Image Features from Scale-Invariant Keypoints
776 Computer Vision Jan-Michael Frahm Spring 2012.
Shape2Pose: Human Centric Shape Analysis CMPT888 Vladimir G. Kim Siddhartha Chaudhuri Leonidas Guibas Thomas Funkhouser Stanford University Princeton University.
SIFT.
Dynamic Geometry Registration Maks Ovsjanikov Leonidas Guibas Natasha GelfandNiloy J. Mitra Simon Flöry Helmut Pottmann Dynamic Geometry Registration.
CENG 789 – Digital Geometry Processing 10- Least-Squares Solutions
Recognizing Deformable Shapes
Geometrically Stable Sampling for the ICP Algorithm
Spectral Methods Tutorial 6 1 © Maks Ovsjanikov
Dynamical Statistical Shape Priors for Level Set Based Tracking
Robust Similarity Measures for Mobile Object Trajectories
CSE 455 – Guest Lectures 3 lectures Contact Interest points 1
Geometric Hashing: An Overview
3D Scan Alignment Using ICP
SIFT.
CENG 789 – Digital Geometry Processing 11- Least-Squares Solutions
Recognition and Matching based on local invariant features
Presentation transcript:

Partial and Approximate Symmetry Detection for 3D Geometry Mark Pauly Niloy J. Mitra Leonidas J. Guibas

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Symmetry in Nature “Symmetry is a complexity-reducing concept [...]; seek it everywhere.” - Alan J. Perlis "Females of several species, including […] humans, prefer symmetrical males." - Chris Evan

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Symmetry for Geometry Processing [Funkhouser et al. `05] [Sharf et al. `04] [Katz and Tal `04] [Khazdan et al. `04]

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Partial Symmetry Detection Given Shape model (represented as point cloud, mesh,... ) Identify and extract similar (symmetric) patches of different size across different resolutions Goal

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Related Work [Podolak et al. `06][Loy and Eklundh `06] Hough transform on feature points [Gal and Cohen-Or `05] tradeoff memory for speed

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Types of Symmetry Transform Types: Reflection Rotation + Translation Uniform Scaling

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Contributions Automatic detection of discrete symmetries ! reflection, rigid transform, uniform scaling Symmetry graphs ! high level structural information about object Output sensitive algorithms ! low memory requirements

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Problem Characteristics Difficulties Which parts are symmetric ! objects not pre-segmented Space of transforms: rotation + translation Brute force search is not feasible Easy Proposed symmetries ! easy to validate

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Reflective Symmetry

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Reflective Symmetry: A Pair Votes

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Reflective Symmetry: Voting Continues

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Reflective Symmetry: Voting Continues

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Reflective Symmetry: Largest Cluster Height of cluster ! size of patch Spread of cluster ! level of approximation

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Pipeline

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Pipeline

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Pruning: Local Signatures Local signature ! invariant under transforms Signatures disagree ! points don’t correspond Use (  1,  2 ) for curvature based pruning

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Reflection: Normal-based Pruning

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Point Pair Pruning all pairs curvature based curvature + normal based

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Transformations Reflection ! point-pairs Rigid transform ! more information Robust estimation of principal curvature frames [Cohen-Steiner et al. `03]

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Mean-Shift Clustering Kernel: Radially symmetric Radius/spread

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Verification Clustering gives a good guess Verify ! build symmetric patches Locally refine solution using ICP algorithm [Besl and McKay `92]

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Random Sampling Height of clusters related to symmetric region size Random samples ! larger regions likely to be detected earlier Output sensitive

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Model Reduction: Chambord

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Model Reduction: Chambord

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Model Reduction: Chambord

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Sydney Opera House

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Sydney Opera House

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Approximate Symmetry: Dragon correction field UNITS: fraction of bounding box diagonal detected symmetries

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Limitations Cannot differentiate between small sized symmetries and comparable noise [Castro et al. `06]

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Articulated Motion: Horses ‘symmetry’ detection between two objects ! registration

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra More details in the paper Symmetry graph reduction Analysis of sampling requirements

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Future Work Detect biased deformation Pose independent shape matching Application to higher dimensional data

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Acknowledgements DARPA, NSF, CARGO, ITR, and NIH grants Stanford Graduate Fellowship Pierre Alliez Mario Botsch Doo Young Kwon Marc Levoy Ren Ng Bob Sumner Dilys Thomas anonymous reviewers

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Thank you! Niloy J. Leonidas J. Mark

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Performance model# verticessign.pairingcluster.verif. Dragon 160, Opera 9, Castle 172, Horse 8, Arch 16, (time in seconds)

Partial and Approximation Symmetry Detection for 3D GeometryNiloy J. Mitra Comparison Podolak et al.Mitra et al. GoalTransformDiscrete symmetry SamplingUniform gridClustering VotingPoints onlyPoints, normals, curvature Symmetry types Planar reflectionreflection, rotation, trans., unif. scaling Detection types Perfect, partial, continuous Perfect, partial, approximate