Dynamic Geometry Registration Maks Ovsjanikov Leonidas Guibas Natasha GelfandNiloy J. Mitra Simon Flöry Helmut Pottmann Dynamic Geometry Registration.

Slides:



Advertisements
Similar presentations
Computer Graphics Lecture 4 Geometry & Transformations.
Advertisements

Developable Surface Fitting to Point Clouds Martin Peternell Computer Aided Geometric Design 21(2004) Reporter: Xingwang Zhang June 19, 2005.
Partial and Approximate Symmetry Detection for 3D Geometry Mark Pauly Niloy J. Mitra Leonidas J. Guibas.
Robust Global Registration Natasha Gelfand Niloy Mitra Leonidas Guibas Helmut Pottmann.
Two-View Geometry CS Sastry and Yang
Modeling the Shape of People from 3D Range Scans
Object Recognition & Model Based Tracking © Danica Kragic Tracking system.
3D Face Modeling Michaël De Smet.
Intelligent Systems Lab. Extrinsic Self Calibration of a Camera and a 3D Laser Range Finder from Natural Scenes Davide Scaramuzza, Ahad Harati, and Roland.
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.
Motion Tracking. Image Processing and Computer Vision: 82 Introduction Finding how objects have moved in an image sequence Movement in space Movement.
CENG 789 – Digital Geometry Processing 06- Rigid-Body Alignment Asst. Prof. Yusuf Sahillioğlu Computer Eng. Dept,, Turkey.
Accurate Non-Iterative O( n ) Solution to the P n P Problem CVLab - Ecole Polytechnique Fédérale de Lausanne Francesc Moreno-Noguer Vincent Lepetit Pascal.
Iterative closest point algorithms
1 GEOMETRIE Geometrie in der Technik H. Pottmann TU Wien SS 2007.
Probabilistic video stabilization using Kalman filtering and mosaicking.
Correspondence & Symmetry
Andrei Sharf Dan A. Alcantara Thomas Lewiner Chen Greif Alla Sheffer Nina Amenta Daniel Cohen-Or Space-time Surface Reconstruction using Incompressible.
UNC Chapel Hill S. Redon - M. C. Lin Rigid body dynamics II Solving the dynamics problems.
1 Numerical geometry of non-rigid shapes Spectral Methods Tutorial. Spectral Methods Tutorial 6 © Maks Ovsjanikov tosca.cs.technion.ac.il/book Numerical.
Niloy J. Mitra1, Natasha Gelfand1, Helmut Pottmann2, Leonidas J
Tracking using the Kalman Filter. Point Tracking Estimate the location of a given point along a sequence of images. (x 0,y 0 ) (x n,y n )
Recovering Articulated Object Models from 3D Range Data Dragomir Anguelov Daphne Koller Hoi-Cheung Pang Praveen Srinivasan Sebastian Thrun Computer Science.
Combining Laser Scans Yong Joo Kil 1, Boris Mederos 2, and Nina Amenta 1 1 Department of Computer Science, University of California at Davis 2 Instituto.
Mobile Robotics: 10. Kinematics 1
3D Geometry for Computer Graphics
Single Point of Contact Manipulation of Unknown Objects Stuart Anderson Advisor: Reid Simmons School of Computer Science Carnegie Mellon University.
Projected image of a cube. Classical Calibration.
COMP 290 Computer Vision - Spring Motion II - Estimation of Motion field / 3-D construction from motion Yongjik Kim.
A Hierarchical Method for Aligning Warped Meshes Leslie Ikemoto 1, Natasha Gelfand 2, Marc Levoy 2 1 UC Berkeley, formerly Stanford 2 Stanford University.
CSCE 641 Computer Graphics: Image-based Modeling (Cont.) Jinxiang Chai.
Introduction Multigrid finite-element solvers using the corotational formulation of finite elements provide an attractive means for the simulation of deformable.
CSE554AlignmentSlide 1 CSE 554 Lecture 8: Alignment Fall 2014.
Computer Graphics Group Tobias Weyand Mesh-Based Inverse Kinematics Sumner et al 2005 presented by Tobias Weyand.
Chapter 9 Superposition and Dynamic Programming 1 Chapter 9 Superposition and dynamic programming Most methods for comparing structures use some sorts.
Functional maps: A Flexible Representation of Maps Between Shapes SIGGRAPH 2012 Maks Ovsjanikov 1 Mirela Ben-Chen 2 Justin Solomon 2 Adrian Butscher 2.
Niloy J. Mitra Leonidas J. Guibas Mark Pauly TU Vienna Stanford University ETH Zurich SIGGRAPH 2007.
Motion and Stress Analysis by Vector Mechanics Edward C. Ting Professor Emeritus of Applied Mechanics Purdue University, West Lafayette, IN National Central.
CSE554AlignmentSlide 1 CSE 554 Lecture 5: Alignment Fall 2011.
MESA LAB Multi-view image stitching Guimei Zhang MESA LAB MESA (Mechatronics, Embedded Systems and Automation) LAB School of Engineering, University of.
Mesh Deformation Based on Discrete Differential Geometry Reporter: Zhongping Ji
IMAGE MOSAICING Summer School on Document Image Processing
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
Metrology 1.Perspective distortion. 2.Depth is lost.
CSE554AlignmentSlide 1 CSE 554 Lecture 8: Alignment Fall 2013.
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.
Temporally Coherent Completion of Dynamic Shapes AUTHORS:HAO LI,LINJIE LUO,DANIEL VLASIC PIETER PEERS,JOVAN POPOVIC,MARK PAULY,SZYMON RUSINKIEWICZ Presenter:Zoomin(Zhuming)
Walking Algorithms for Point Location Roman Soukal Ivana Kolingerová.
Optical Flow. Distribution of apparent velocities of movement of brightness pattern in an image.
Skuller: A volumetric shape registration algorithm for modeling skull deformities Yusuf Sahillioğlu 1 and Ladislav Kavan 2 Medical Image Analysis 2015.
DYNAMICS CONTENTS.
Determining 3D Structure and Motion of Man-made Objects from Corners.
Affine Registration in R m 5. The matching function allows to define tentative correspondences and a RANSAC-like algorithm can be used to estimate the.
Scale Selection for Classification of Point-sampled 3-D Surfaces Jean-François Lalonde, Ranjith Unnikrishnan, Nicolas Vandapel and Martial Hebert Carnegie.
Motivation 2 groups of tools for free-from design Images credits go out to the FiberMesh SIGGRAPH presentation and other sources courtesy of Google.
CENG 789 – Digital Geometry Processing 07- Rigid-Body Alignment Asst. Prof. Yusuf Sahillioğlu Computer Eng. Dept,, Turkey.
11/25/03 3D Model Acquisition by Tracking 2D Wireframes Presenter: Jing Han Shiau M. Brown, T. Drummond and R. Cipolla Department of Engineering University.
CSE 554 Lecture 8: Alignment
CENG 789 – Digital Geometry Processing 08- Rigid-Body Alignment
Motion Segmentation with Missing Data using PowerFactorization & GPCA
René Vidal and Xiaodong Fan Center for Imaging Science
Morphing and Shape Processing
You can check broken videos in this slide here :
Geometrically Stable Sampling for the ICP Algorithm
CENG 789 – Digital Geometry Processing 09- Rigid-Body Alignment
--- Range Image Registration
Presentation transcript:

Dynamic Geometry Registration Maks Ovsjanikov Leonidas Guibas Natasha GelfandNiloy J. Mitra Simon Flöry Helmut Pottmann Dynamic Geometry Registration

Scan Registration

Dynamic Geometry Registration Scan Registration Solve for inter-frame motion:

Dynamic Geometry Registration Scan Registration Solve for inter-frame motion:

Dynamic Geometry Registration The Setup Given: A set of frames {P 0, P 1,... P n } Goal: Recover rigid motion {  1,  2,...  n } between adjacent frames

Dynamic Geometry Registration The Setup Smoothly varying object motion Unknown correspondence between scans Fast acquisition ! motion happens between frames

Dynamic Geometry Registration Contributions Rigid registration ! kinematic property of space- time surface (locally exact) Registration ! surface normal estimation Analysis (see paper for details) Relation to ICP (Iterated Closest Point) Stability analysis Extension to deformable/articulated bodies

Dynamic Geometry Registration Time Ordered Scans tjtj t j+1 t j+2

Dynamic Geometry Registration Space-time Surface

Dynamic Geometry Registration Space-time Surface !

Dynamic Geometry Registration Space-time Surface !

Dynamic Geometry Registration Spacetime Velocity Vectors Tangential point movement ! velocity vectors orthogonal to surface normals

Dynamic Geometry Registration Spacetime Velocity Vectors Tangential point movement ! velocity vectors orthogonal to surface normals

Dynamic Geometry Registration Final Steps (rigid) velocity vectors !

Dynamic Geometry Registration Final Steps (rigid) velocity vectors !

Dynamic Geometry Registration Registration Algorithm 1.Compute time coordinate spacing (  ), and form space-time surface. 2.Compute space time neighborhood using ANN, and locally estimate space-time surface normals. 3.Solve linear system to estimate (c j,c j ). 4.Convert velocity vectors to rotation matrix + translation vector using Plücker coordinates and quarternions.

Dynamic Geometry Registration Normal Estimation: PCA Based Plane fitting using PCA using chosen neighborhood points.

Dynamic Geometry Registration Normal Estimation: Iterative Refinement Update neighborhood with current velocity estimate.

Dynamic Geometry Registration Normal Refinement: Effect of Noise Stable, but more expensive.

Dynamic Geometry Registration Normal Estimation: Local Triangulation Perform local surface triangulation (tetrahedralization).

Dynamic Geometry Registration Normal Estimation Stable, but more expensive.

Dynamic Geometry Registration Comparison with ICP ICP point-planeDynamic registration

Dynamic Geometry Registration Rigid: Bee Sequence (2,200 frames)

Dynamic Geometry Registration Rigid: Coati Sequence (2,200 frames)

Dynamic Geometry Registration Handling Large Number of Frames

Dynamic Geometry Registration Rigid/Deformable: Teapot Sequence (2,200 frames)

Dynamic Geometry Registration Deformable Bodies Cluster points, and solve smaller systems. Propagate solutions with regularization.

Dynamic Geometry Registration Deformable: Hand (100 frames)

Dynamic Geometry Registration Deformable: Hand (100 frames) scan #1 ! scan #50 scan #1 ! scan #100

Dynamic Geometry Registration Deformation + scanner motion: Skeleton (100 frames)

Dynamic Geometry Registration Deformation + scanner motion: Skeleton (100 frames) scan #1 ! scan #50 scan #1 ! scan #100

Dynamic Geometry Registration Deformation + scanner motion: Skeleton (100 frames) rigid components

Dynamic Geometry Registration Performance Table (on 2.4GHz Athlon Dual Core, 2GB RAM)

Dynamic Geometry Registration Conclusion Simple algorithm using kinematic properties of space-time surface. Easy modification for deformable bodies. Suitable for use with fast scanners.

Dynamic Geometry Registration Conclusion Simple algorithm using kinematic properties of space-time surface. Easy modification for deformable bodies. Suitable for use with fast scanners. Limitations/Future Work Need more scans, dense scans, … Sampling condition ! time and space

Dynamic Geometry Registration Acknowledgements Thibaut Weise Andreas Schilling Funding sources: Austrian Science Fund grants S9206-N12 and P18865-N13 Neumaier fellowship NSF ITR NIH grant GM DARPA grant Agilent Corporation

Dynamic Geometry Registration thank you