Animation From Observation: Motion Editing Dan Kong CMPS 260 Final Project.

Slides:



Advertisements
Similar presentations
Active Shape Models Suppose we have a statistical shape model –Trained from sets of examples How do we use it to interpret new images? Use an “Active Shape.
Advertisements

The fundamental matrix F
Verbs and Adverbs: Multidimensional Motion Interpolation Using Radial Basis Functions Presented by Sean Jellish Charles Rose Michael F. Cohen Bobby Bodenheimer.
On Constrained Optimization Approach To Object Segmentation Chia Han, Xun Wang, Feng Gao, Zhigang Peng, Xiaokun Li, Lei He, William Wee Artificial Intelligence.
Interactive Motion Editing Presented by Troy McMahon.
HCI 530 : Seminar (HCI) Damian Schofield.
CSCE 441 Computer Graphics: Keyframe Animation/Smooth Curves Jinxiang Chai.
CHAPTER 4 Image Enhancement in Frequency Domain
09/11/2006 Bharathi Manivannan A.S Motion Warping International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH’95 - -Andrew Witkin.
Contents Description of the big picture Theoretical background on this work The Algorithm Examples.
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
Curve Analogies Aaron Hertzmann Nuria Oliver Brain Curless Steven M. Seitz University of Washington Microsoft Research Thirteenth Eurographics.
Wavelet Transform. What Are Wavelets? In general, a family of representations using: hierarchical (nested) basis functions finite (“compact”) support.
Behavior Planning for Character Animation Manfred Lau and James Kuffner Carnegie Mellon University.
Previously Two view geometry: epipolar geometry Stereo vision: 3D reconstruction epipolar lines Baseline O O’ epipolar plane.
Retargetting Motion to New Characters Michael Gleicher SIGGRAPH 98.
2D Fourier Theory for Image Analysis Mani Thomas CISC 489/689.
Hierarchical Transformations Hierarchical Models Scene Graphs
Automatic Camera Calibration
ENG4BF3 Medical Image Processing
Image Processing1 Image Filtering Filtering can be use to enhance some features and de- enhance others. Usually used as a pre-processing step.
Curve Modeling Bézier Curves
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.
1 CMT Fundamentals of Computer Graphics Revision Dr. Xiaohong Gao BG---Room 2C23 Week 11.
Graphite 2004 Statistical Synthesis of Facial Expressions for the Portrayal of Emotion Lisa Gralewski Bristol University United Kingdom
Course 12 Calibration. 1.Introduction In theoretic discussions, we have assumed: Camera is located at the origin of coordinate system of scene.
ALIGNMENT OF 3D ARTICULATE SHAPES. Articulated registration Input: Two or more 3d point clouds (possibly with connectivity information) of an articulated.
Motion Editing (Geometric and Constraint-Based Methods) Jehee Lee.
High-Resolution Interactive Panoramas with MPEG-4 발표자 : 김영백 임베디드시스템연구실.
INFORMATIK Laplacian Surface Editing Olga Sorkine Daniel Cohen-Or Yaron Lipman Tel Aviv University Marc Alexa TU Darmstadt Christian Rössl Hans-Peter Seidel.
Jinxiang Chai Composite Transformations and Forward Kinematics 0.
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.
Detail-Preserving Fluid Control N. Th ű rey R. Keiser M. Pauly U. R ű de SCA 2006.
8-1 Chapter 8: Image Restoration Image enhancement: Overlook degradation processes, deal with images intuitively Image restoration: Known degradation processes;
B-spline Wavelets Jyun-Ming Chen Spring Basic Ideas Here refers to cubic B-spline –most commonly used in CG Assume cardinal cubic B-spline for now.
Chapter 9 Advanced Assembly Modeling Techniques. After completing this chapter, you will be able to perform the following: –Create sketch blocks –Create.
1/20 System Overview Cyclic mo-cap data (walking, running..) Cyclic mo-cap data (walking, running..) Music / Sound (audio) Music / Sound (audio) Resulting.
CSCE 441 Computer Graphics: Keyframe Animation/Smooth Curves Jinxiang Chai.
Computer Graphics 3D Transformations. Translation.
(c) 2000, 2001 SNU CSE Biointelligence Lab Finding Region Another method for processing image  to find “regions” Finding regions  Finding outlines.
CSCE 441 Computer Graphics: Keyframe Animation/Smooth Curves Jinxiang Chai.
Syed ardi syed yahya kamal 2011 chapter five.  Creating in-between positions is still a hallmark of animation.  Using techniques called interpolation.
Rick Parent - CIS681 Motion Capture Use digitized motion to animate a character.
October 16, 2014Computer Vision Lecture 12: Image Segmentation II 1 Hough Transform The Hough transform is a very general technique for feature detection.
Flexible Automatic Motion Blending with Registration Curves
3D Geometric Transformation
CSCE 441: Keyframe Animation/Smooth Curves (Cont.) Jinxiang Chai.
CSCE 441: Keyframe Animation/Smooth Curves (Cont.) Jinxiang Chai.
Chapter 9 Advanced Assembly Modeling Techniques. After completing this chapter, you will be able to perform the following: –Create sketch blocks –Create.
Application: Multiresolution Curves Jyun-Ming Chen Spring 2001.
2006/10/25 1 A Virtual Endoscopy System Author : Author : Anna Vilanova 、 Andreas K ö nig 、 Eduard Gr ö ller Source :Machine Graphics and Vision, 8(3),
Spring 2014 CS274: Automatic Rigging
Statistical Models of Appearance for Computer Vision 主講人:虞台文.
: Chapter 5: Image Filtering 1 Montri Karnjanadecha ac.th/~montri Image Processing.
Instructor: Mircea Nicolescu Lecture 5 CS 485 / 685 Computer Vision.
Constrained Synthesis of Textural Motion for Animation Shmuel Moradoff Dani Lischinski The Hebrew University of Jerusalem.
1 Teaching Innovation - Entrepreneurial - Global The Centre for Technology enabled Teaching & Learning, N Y S S, India DTEL DTEL (Department for Technology.
End effector End effector - the last coordinate system of figure Located in joint N. But usually, we want to specify it in base coordinates. 1.
Correspondence and Stereopsis. Introduction Disparity – Informally: difference between two pictures – Allows us to gain a strong sense of depth Stereopsis.
Chapter 9 Advanced Assembly Modeling Techniques. After completing this chapter, you will be able to perform the following: –Create design view representations.
Multiresolution Analysis (Section 7.1) CS474/674 – Prof. Bebis.
CS4670 / 5670: Computer Vision Kavita Bala Lecture 20: Panoramas.
CSCE 441 Computer Graphics: Keyframe Animation/Smooth Curves
Computer Graphics 3D Transformations
Motion and Optical Flow
CSCE 441 Computer Graphics: Keyframe Animation/Smooth Curves
Line and Character Attributes 2-D Transformation
Synthesis of Motion from Simple Animations
Course 6 Stereo.
Presentation transcript:

Animation From Observation: Motion Editing Dan Kong CMPS 260 Final Project

Why we need motion editing Why we need motion editing Reuse motion capture data to different character and different actionsReuse motion capture data to different character and different actions Create infeasible motion which is hard to get by using motion captureCreate infeasible motion which is hard to get by using motion capture Change of intent which can not be predicted before the motion caputreChange of intent which can not be predicted before the motion caputre

In this project, I will implement a prototype motion editing system that has the following features Multiresolution motion filteringMultiresolution motion filtering Multitarget motion interpolationMultitarget motion interpolation Motion path editingMotion path editing

What is Motion Multiresolution filtering Basically, it is a technique that originally used in image processing now applied to the motion parameters of an articulated figure.Basically, it is a technique that originally used in image processing now applied to the motion parameters of an articulated figure. Intuition of this method: low frequencies contain gross and smooth motion while high frequencies contain detail, abrupt motion and most of the noise.Intuition of this method: low frequencies contain gross and smooth motion while high frequencies contain detail, abrupt motion and most of the noise.

Motion filtering algorithm The number of frames determine how many frequency bands (fb) for each signal: let 2 n < m < 2 n+1, then fb = n.The number of frames determine how many frequency bands (fb) for each signal: let 2 n < m < 2 n+1, then fb = n. Calculate the low-pass sequence of all fb signal by convolving the signal with a low-pass filter, obtaining G k, G k-1...G 0 where G fb is the DC component of the signal (0=<k<=fb)Calculate the low-pass sequence of all fb signal by convolving the signal with a low-pass filter, obtaining G k, G k-1...G 0 where G fb is the DC component of the signal (0=<k<=fb) Obtain the band- pass filter bands: L k = G k – G k+1Obtain the band- pass filter bands: L k = G k – G k+1

Motion filtering algorithm (continued) Adjust gains for each band and multiply L k by their current gain values.Adjust gains for each band and multiply L k by their current gain values. Reconstruct the motion signal:Reconstruct the motion signal: G 0 = G fb + G 0 = G fb +

Multitarget motion interpolation A process widely used in computer animation to blend between different models.A process widely used in computer animation to blend between different models. Facial animation: By blending the corresponding parameters of different face, we can control the expression.Facial animation: By blending the corresponding parameters of different face, we can control the expression. A happy walk + a sad walk = ?A happy walk + a sad walk = ?

Multitarget motion interpolation (continued) Mix multitarget interpolation and multiresolution filtering to blend the frequency bands of two or more motion separately.Mix multitarget interpolation and multiresolution filtering to blend the frequency bands of two or more motion separately. Need to establish the time correspondence between two signals.Need to establish the time correspondence between two signals.

Motion path editing What is path editing: – –Altering previously motion capture data to follow a different path Why Path Editing: - Using original motion in a new environment - Dynamic application: walking to a goal location

Alternative Approach Capture all desired motionsCapture all desired motions Disadvantages of this approach:Disadvantages of this approach: - Can not possible predict every possible required motion - Can not possible predict every possible required motion - Such a motion library are expensive to create - Such a motion library are expensive to create - Unwieldy to control as it expands - Unwieldy to control as it expands

Algorithm Overview Basic Idea:Basic Idea: Represent the motion relative to the path. As the path is altered, the orientation of character updates accordingly. Represent the motion relative to the path. As the path is altered, the orientation of character updates accordingly. AlgorithmAlgorithm - Automatic path generation - Automatic path generation - Calculate initial path coordinate system - Calculate initial path coordinate system - Path Editing - Path Editing - Computing the changed path coordinate system - Computing the changed path coordinate system

Why B-SplineWhy B-Spline –Local control without affecting global shape –continuous Path Coordinate RepresentationPath Coordinate Representation - p(t) is the coordinate center. The corresponding - p(t) is the coordinate center. The corresponding transformation matrix is P(t) transformation matrix is P(t) - R(t) is the orientation of the coordinate system. - R(t) is the orientation of the coordinate system. - P(t)R(t) is the path’s coordinate system - P(t)R(t) is the path’s coordinate system - R(t) -1 P(t) -1 is the transformation from global to path’s - R(t) -1 P(t) -1 is the transformation from global to path’s local coordinate system local coordinate system Path Description

Initial Path Generation Least-Square FittingLeast-Square Fitting –Using the root translation as the fitting point. –Compute average Y translation to constrain the path to lie in X-Z plane. path to lie in X-Z plane. –Store the R 0 (t) -1 P 0 (t) -1 for later editing

Path Editing After Altering the curveAfter Altering the curve –P(t)R(t) R 0 (t) -1 P 0 (t) -1 is computed as the coordinate system for the new path coordinate system for the new path –Once the P(t) is updated, the corresponding R(t) must be computed accordingly must be computed accordingly

Future Work Generate more frames when the path is strechedGenerate more frames when the path is streched Add constraint to avoid geometric violation.Add constraint to avoid geometric violation.

References “Motion Path Editing” “Motion Signal Processing” “Motion Warping” “Multiresolution Curves” “Hierarchical B-Spline refinement”

Thanks!!!