Multiresolution Motion Analysis with Applications Jehee Lee Sung Yong Shin Dept of EE&CS, KAIST Jehee Lee Sung Yong Shin Dept of EE&CS, KAIST.

Slides:



Advertisements
Similar presentations
11/11/02 IDR Workshop Dealing With Location Uncertainty in Images Hasan F. Ates Princeton University 11/11/02.
Advertisements

As-Rigid-As-Possible Surface Modeling
Synchronized Multi-character Motion Editing Manmyung Kim, Kyunglyul Hyun, Jongmin Kim, Jehee Lee Seoul National University.
University of Ioannina - Department of Computer Science Wavelets and Multiresolution Processing (Background) Christophoros Nikou Digital.
Multiscale Analysis of Images Gilad Lerman Math 5467 (stealing slides from Gonzalez & Woods, and Efros)
Ted Adelson’s checkerboard illusion. Motion illusion, rotating snakes.
Slides from Alexei Efros
CS 691 Computational Photography
IMAGE UPSAMPLING VIA IMPOSED EDGE STATISTICS Raanan Fattal. ACM Siggraph 2007 Presenter: 이성호.
Trajectory Generation
Summary & Homework Jinxiang Chai. Outline Motion data process paper summary Presentation tips Homework Paper assignment.
Interactive Motion Editing Presented by Troy McMahon.
Introduction to Data-driven Animation Jinxiang Chai Computer Science and Engineering Texas A&M University.
Convolution. Spatial Filtering Operations g(x,y) = 1/M  f(n,m) (n,m) in  S Example 3 x 3 5 x 5.
Sampling and Pyramids : Rendering and Image Processing Alexei Efros …with lots of slides from Steve Seitz.
Fast Texture Synthesis using Tree-structured Vector Quantization Li-Yi Wei Marc Levoy Computer Graphics Group Stanford University.
09/11/2006 Bharathi Manivannan A.S Motion Warping International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH’95 - -Andrew Witkin.
Kinematics. ILE5030 Computer Animation and Special Effects2 Kinematics The branch of mechanics concerned with the motions of objects without regard to.
Retargetting Motion to New Characters Michael Gleicher SIGGRAPH 98.
Visualization and graphics research group CIPIC Feb 18, 2003Multiresolution (ECS 289L) - Winter Progressive Meshes (SIGGRAPH ’96) By Hugues Hoppe.
2D Fourier Theory for Image Analysis Mani Thomas CISC 489/689.
Rotation and Orientation: Affine Combination Jehee Lee Seoul National University.
Robust Motion Watermarking based on Multiresolution Analysis EUROGRAPHICS 2000 Speaker: 彭任右, GAME Lab Date: 4/18/2005.
1 © Netskills Quality Internet Training, University of Newcastle Flash 8: Animation Techniques © Netskills, Quality Internet Training, University of Newcastle.
1.  Introduction  Gaussian and Laplacian pyramid  Application Salient region detection Edge-aware image processing  Conclusion  Reference 2.
ENG4BF3 Medical Image Processing
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5409 T-R 10:30am – 11:50am.
1 Methods in Image Analysis – Lecture 3 Fourier U. Pitt Bioengineering 2630 CMU Robotics Institute Spring Term, 2006 George Stetten, M.D., Ph.D.
Projective Texture Atlas for 3D Photography Jonas Sossai Júnior Luiz Velho IMPA.
Motion Blending (Multidimensional Interpolation) Jehee Lee.
Computer Graphics Group Tobias Weyand Mesh-Based Inverse Kinematics Sumner et al 2005 presented by Tobias Weyand.
Motion Editing (Geometric and Constraint-Based Methods) Jehee Lee.
Robust Motion Watermarking based on Multiresolution Analysis Tae-hoon Kim Jehee Lee Sung Yong Shin Korea Advanced Institute of Science and Technology.
High-Resolution Interactive Panoramas with MPEG-4 발표자 : 김영백 임베디드시스템연구실.
Image Processing Xuejin Chen Ref:
1 Fundamentals of Robotics Linking perception to action 2. Motion of Rigid Bodies 南台科技大學電機工程系謝銘原.
Image Processing Edge detection Filtering: Noise suppresion.
INFORMATIK Laplacian Surface Editing Olga Sorkine Daniel Cohen-Or Yaron Lipman Tel Aviv University Marc Alexa TU Darmstadt Christian Rössl Hans-Peter Seidel.
A Hierarchical Approach to Interactive Motion Editing for Human-like Figures Jehee Lee Sung Yong Shin KAIST Jehee Lee Sung Yong Shin KAIST.
Coordinate-Invariant Methods For Motion Analysis and Synthesis Jehee Lee Dept. Of Electric Engineering and Computer Science Korea Advanced Institute of.
EEE. Dept of HONG KONG University of Science and Technology Introduction to Robotics Page 1 Lecture 2. Rigid Body Motion Main Concepts: Configuration Space.
Computer Vision Spring ,-685 Instructor: S. Narasimhan Wean 5403 T-R 3:00pm – 4:20pm.
2D Texture Synthesis Instructor: Yizhou Yu. Texture synthesis Goal: increase texture resolution yet keep local texture variation.
Comparing Two Motions Jehee Lee Seoul National University.
Character Animation and Control using Human Motion Data Jehee Lee Carnegie Mellon University
Rick Parent - CIS681 Motion Capture Use digitized motion to animate a character.
Flexible Automatic Motion Blending with Registration Curves
1 Methods in Image Analysis – Lecture 3 Fourier CMU Robotics Institute U. Pitt Bioengineering 2630 Spring Term, 2004 George Stetten, M.D., Ph.D.
CS559: Computer Graphics Final Review Li Zhang Spring 2010.
Application: Multiresolution Curves Jyun-Ming Chen Spring 2001.
(c) 2002 University of Wisconsin, CS 559
Animation From Observation: Motion Editing Dan Kong CMPS 260 Final Project.
Speaker Min-Koo Kang March 26, 2013 Depth Enhancement Technique by Sensor Fusion: MRF-based approach.
Computer vision. Applications and Algorithms in CV Tutorial 3: Multi scale signal representation Pyramids DFT - Discrete Fourier transform.
Constrained Synthesis of Textural Motion for Animation Shmuel Moradoff Dani Lischinski The Hebrew University of Jerusalem.
MAY 14, 2007 MULTIMEDIA FRAMEWORK LAB YOON, DAE-IL THE STEERABLE PYRAMID : A FLEXIBLE ARCHITECTURE FOR MULTI- SCALE DERIVATIVE COMPUTATION.
Wavelets Chapter 7 Serkan ERGUN. 1.Introduction Wavelets are mathematical tools for hierarchically decomposing functions. Regardless of whether the function.
Iterative Techniques for Image Interpolation
Presented by 翁丞世  View Interpolation  Layered Depth Images  Light Fields and Lumigraphs  Environment Mattes  Video-Based.
Recall: Gaussian smoothing/sampling G 1/4 G 1/8 Gaussian 1/2 Solution: filter the image, then subsample Filter size should double for each ½ size reduction.
Image Resampling & Interpolation
Multiresolution Analysis (Chapter 7)
Jeremy Bolton, PhD Assistant Teaching Professor
Multiscale Analysis of Images
Coordinate-Invariant Methods For Motion Analysis and Synthesis
Image Transforms for Robust Coding
Image Stitching Computer Vision CS 678
Synthesis of Motion from Simple Animations
Image Resampling & Interpolation
Filtering Images Work in the spatial domain
Presentation transcript:

Multiresolution Motion Analysis with Applications Jehee Lee Sung Yong Shin Dept of EE&CS, KAIST Jehee Lee Sung Yong Shin Dept of EE&CS, KAIST

Contents 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications

Character Animation Realistic motion data Motion capture technologyMotion capture technology Commercial librariesCommercial libraries Producing animation from available motion clips requires specialized toolsrequires specialized tools –interactive editing, smoothing, enhancement, blending, stitching, and so on stimulates the need for a unified approachstimulates the need for a unified approach Realistic motion data Motion capture technologyMotion capture technology Commercial librariesCommercial libraries Producing animation from available motion clips requires specialized toolsrequires specialized tools –interactive editing, smoothing, enhancement, blending, stitching, and so on stimulates the need for a unified approachstimulates the need for a unified approach

Multiresolution Analysis Representing a signal at multiple resolutions gives hierarchy of successively smoother signalsgives hierarchy of successively smoother signals facilitates a variety of signal processing tasksfacilitates a variety of signal processing tasks Representing a signal at multiple resolutions gives hierarchy of successively smoother signalsgives hierarchy of successively smoother signals facilitates a variety of signal processing tasksfacilitates a variety of signal processing tasks

Previous Work Image and signal processing Gauss-Laplacian pyramid [Burt and Adelson 83]Gauss-Laplacian pyramid [Burt and Adelson 83] Texture analysis and synthesis, image editing, curve and surface manipulation, data compression, and so onTexture analysis and synthesis, image editing, curve and surface manipulation, data compression, and so on Motion synthesis and editing Hierarchical spacetime control [Liu, Gortler and Cohen 94]Hierarchical spacetime control [Liu, Gortler and Cohen 94] Motion signal processing [Bruderlin and Williams 95]Motion signal processing [Bruderlin and Williams 95] Image and signal processing Gauss-Laplacian pyramid [Burt and Adelson 83]Gauss-Laplacian pyramid [Burt and Adelson 83] Texture analysis and synthesis, image editing, curve and surface manipulation, data compression, and so onTexture analysis and synthesis, image editing, curve and surface manipulation, data compression, and so on Motion synthesis and editing Hierarchical spacetime control [Liu, Gortler and Cohen 94]Hierarchical spacetime control [Liu, Gortler and Cohen 94] Motion signal processing [Bruderlin and Williams 95]Motion signal processing [Bruderlin and Williams 95]

Issues in Motion Analysis Difficulties in handling motion data Inherent non-linearity of orientation spaceInherent non-linearity of orientation spaceCoordinate-invariance Independent of the choice of coordinate framesIndependent of the choice of coordinate frames Difficulties in handling motion data Inherent non-linearity of orientation spaceInherent non-linearity of orientation spaceCoordinate-invariance Independent of the choice of coordinate framesIndependent of the choice of coordinate frames

Contents 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications

Motion Representation Configuration of articulated figures Bundle of motion signalsBundle of motion signals Each signal represents time-varying positions and orientationsEach signal represents time-varying positions and orientations Rigid transformationRigid transformation Configuration of articulated figures Bundle of motion signalsBundle of motion signals Each signal represents time-varying positions and orientationsEach signal represents time-varying positions and orientations Rigid transformationRigid transformation

Decomposition Expansion : up-sampling followed by smoothing Reduction : smoothing followed by down-sampling Expansion : up-sampling followed by smoothing Reduction : smoothing followed by down-sampling Reduction Expansion

Decomposition and Reconstruction DecompositionReconstructionDecompositionReconstruction

Our Approach Multiresolution Motion Analysis Hierarchical displacement mappingHierarchical displacement mapping –How to represent –Displacement mapping [Bruderlin and Williams 95] –Motion warping [Popovic and Witkin 95] Spatial filtering for motion dataSpatial filtering for motion data –How to construct –Implement reduction and expansion Multiresolution Motion Analysis Hierarchical displacement mappingHierarchical displacement mapping –How to represent –Displacement mapping [Bruderlin and Williams 95] –Motion warping [Popovic and Witkin 95] Spatial filtering for motion dataSpatial filtering for motion data –How to construct –Implement reduction and expansion

Contents 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications

Motion Displacement global (fixed) reference frame

Motion Displacement global (fixed) reference frame

Hierarchical Displacement Mapping

A series of successively refined motions Coordinate-independentCoordinate-independent –measured in a body-fixed coordinate frame UniformityUniformity –through a local parameterization A series of successively refined motions Coordinate-independentCoordinate-independent –measured in a body-fixed coordinate frame UniformityUniformity –through a local parameterization Hierarchical Displacement Mapping

Contents 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications

Spatial Filtering for Orientation Data Linear shift-invariant (LSI) filter filter mask :filter mask : vector-valued signal :vector-valued signal : Not suitable for unit quaternion data unit-length constraintsunit-length constraints Linear shift-invariant (LSI) filter filter mask :filter mask : vector-valued signal :vector-valued signal : Not suitable for unit quaternion data unit-length constraintsunit-length constraints

Previous Work Re-normalization Azuma and Bishop (‘94)Azuma and Bishop (‘94) Exploit a local parameterization Lee and Shin (‘96)Lee and Shin (‘96) Welch and Bishop (‘97)Welch and Bishop (‘97) Fang et al. (‘98)Fang et al. (‘98) Hsieh et al. (‘98)Hsieh et al. (‘98) –lack of crucial filter properties Re-normalization Azuma and Bishop (‘94)Azuma and Bishop (‘94) Exploit a local parameterization Lee and Shin (‘96)Lee and Shin (‘96) Welch and Bishop (‘97)Welch and Bishop (‘97) Fang et al. (‘98)Fang et al. (‘98) Hsieh et al. (‘98)Hsieh et al. (‘98) –lack of crucial filter properties

Basic Idea Exploit correspondence in differential spaces Linear motion :Linear motion : Angular motion :Angular motion : Exploit correspondence in differential spaces Linear motion :Linear motion : Angular motion :Angular motion : Velocity Acceleration

Transformation Transformation between linear and angular signals

Filter Design Given: spatial filter F Output: spatial filter H for orientation data “Unitariness” is guaranteed“Unitariness” is guaranteed Given: spatial filter F Output: spatial filter H for orientation data “Unitariness” is guaranteed“Unitariness” is guaranteed

Filter Design Given: spatial filter F Output: spatial filter H for orientation data Local supportLocal support –#support( H ) = #support( F ) Given: spatial filter F Output: spatial filter H for orientation data Local supportLocal support –#support( H ) = #support( F )

Properties of Orientation Filters Coordinate-invarianceTime-invarianceSymmetryCoordinate-invarianceTime-invarianceSymmetry

Examples (1) Blurring by binomial masks Original Angular acceleration Filtered Original Filtered Original Filtered

Examples (2) SmoothingSmoothing Original Angular acceleration Filtered Original Filtered Original Filtered

Examples (3) High-frequency boosting Original Angular acceleration Filtered Original Filtered Original Filtered

Our scheme vs. Re-normalization Re-normalizationOur scheme Filtering with an average filter

Coordinate Frame-Invariance Decomposition Reconstruction

Contents 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications 1.Introduction 2.Multiresolution Analysis 3.Hierarchical Displacement Mapping 4.Spatial Filtering for Motion Data 5.Applications

Enhancement / Attenuation Level-wise scaling of coefficients

Motion Blending Combine multiple motions together select a base signal and details from different examplesselect a base signal and details from different examples Combine multiple motions together select a base signal and details from different examplesselect a base signal and details from different examples straight walking straight walking turning with a walk turning with a walk straight limping straight limping turning with a limp turning with a limp

Motion Blending

Motion Stitching A simple approach Estimate velocities at boundaries, thenEstimate velocities at boundaries, then Perform -interpolationPerform -interpolation A simple approach Estimate velocities at boundaries, thenEstimate velocities at boundaries, then Perform -interpolationPerform -interpolation

Motion Stitching A simple approach Estimate velocities at boundaries, thenEstimate velocities at boundaries, then Perform -interpolationPerform -interpolation A simple approach Estimate velocities at boundaries, thenEstimate velocities at boundaries, then Perform -interpolationPerform -interpolation

Motion Stitching Difficulties of the simple approach Hard to estimate velocity robustlyHard to estimate velocity robustly Difficulties of the simple approach Hard to estimate velocity robustlyHard to estimate velocity robustly

Motion Stitching Stitching motion clips seamlessly Merging coefficients level-by-levelMerging coefficients level-by-level Stitching motion clips seamlessly Merging coefficients level-by-levelMerging coefficients level-by-level WalkingRunning

Motion Stitching Stitching motion clips seamlessly Merging coefficients level-by-levelMerging coefficients level-by-level Stitching motion clips seamlessly Merging coefficients level-by-levelMerging coefficients level-by-level WalkingRunning

Motion Stitching Stitching motion clips seamlessly Merging coefficients level-by-levelMerging coefficients level-by-level Stitching motion clips seamlessly Merging coefficients level-by-levelMerging coefficients level-by-level stub a toelimpstitching

System Demonstration

Conclusion Multiresolution motion Analysis Coherency in positions and orientationsCoherency in positions and orientations Coordinate-invarianceCoordinate-invariance Multiresolution motion Analysis Coherency in positions and orientationsCoherency in positions and orientations Coordinate-invarianceCoordinate-invariance