Motion Texture: A Two-Level Statistical Model for Character Motion Synthesis SIGGRAPH ‘02 Speaker: Alvin Date: 3 August 2004.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

Active Appearance Models
Mining Frequent Spatio-temporal Sequential Patterns
DETECTING REGIONS OF INTEREST IN DYNAMIC SCENES WITH CAMERA MOTIONS.
Motion Capture Assisted Animation: Texturing and Synthesis SIGGRAPH ’02 Speaker: Alvin Date:23 August 2004.
Hidden Markov Models Theory By Johan Walters (SR 2003)
Progress on the Control of Nonholonomic Systems
Physically Based Motion Transformation Zoran Popović Andrew Witkin SIGGRAPH ‘99.
Introduction to Data-driven Animation Jinxiang Chai Computer Science and Engineering Texas A&M University.
Modeling Pixel Process with Scale Invariant Local Patterns for Background Subtraction in Complex Scenes (CVPR’10) Shengcai Liao, Guoying Zhao, Vili Kellokumpu,
Exchanging Faces in Images SIGGRAPH ’04 Blanz V., Scherbaum K., Vetter T., Seidel HP. Speaker: Alvin Date: 21 July 2004.
McGraw-Hill/Irwin © 2003 The McGraw-Hill Companies, Inc.,All Rights Reserved. 肆 資料分析與表達.
An Evaluation of a Cost Metric for Selecting Transitions between Motion Segments EG SCA ’03 Speaker: Alvin Date: 4 October 2004.
Synthesizing Physically Realistic Human Motion in Low-Dimensional, Behavior- Specific Spaces SIGGRAPH ’ 04 Speaker: Alvin Date: 13 July 2004.
Modeling and Deformation of Arms and Legs Based on Ellipsoidal Sweeping Speaker: Alvin Date:2/16/2004From:PG03.
A Data-Driven Approach to Quantifying Natural Human Motion SIGGRAPH ’ 05 Liu Ren, Alton Patrick, Alexei A. Efros, Jassica K. Hodgins, and James M. Rehg.
論文研討 2 學分 授課教師:吳俊概.
1 數位控制(一) 2 數位控制 課程計畫 課程目標 介紹數位控制理論 與工業界常用之數位控制器比較 實習數位控制器之模擬與設計 課程綱要 Introduction to Digital Control System The z Transform z-Plane Analysis of Discrete-Time.
Motion Path Editing I3D 2001 Speaker: Alvin Date: 5/31/04.
Representing Animation by Principal Components EUROGRAPHICS 2000 Speaker: Alvin Date: 4/18/2005.
A Geometry-based Soft Shadow Volume Algorithm using Graphics Hardware Speaker: Alvin Date:2003/7/23 SIGGRAPH 2003 Ulf Assarsson Tomas Akenine-Moller.
Motion Doodles: An Interface for Sketching Character Motion SIGGRAPH ’04 Speaker: Alvin Date: 5 July 2004.
Retargetting Motion to New Characters SIGGRAPH ’98 Speaker: Alvin Date: 6 July 2004.
Shadow Volumes on Programmable Graphics Hardware Speaker: Alvin Date: 2003/11/3 EUROGRAPHICS 2003.
Motion Map: Image-based Retrieval and Segmentation of Motion Data EG SCA ’04 Speaker: Alvin Date: 11/29/2004.
1 高等演算法 授課老師 : 陳建源 研究室 : 法 401 網站
研究資料的分析. 資料分析的基本策略  General data analysis strategies 1.Sketching ideas 2.Taking notes 3.Summarize field nores 4.Getting feedback on ideas 5.Working with.
Object Detection and Tracking Mike Knowles 11 th January 2005
Recording a Game of Go: Hidden Markov Model Improves Weak Classifier Steven Scher
Penumbra Maps: Approximate Soft Shadows in Real-Time Chris Wyman and Charles Hansen University of Utah Speaker: Alvin Date: 9/29/2003 EUROGRAPH 2003.
Continuum Crowds Adrien Treuille, Siggraph 王上文.
Collaborative Ordinal Regression Shipeng Yu Joint work with Kai Yu, Volker Tresp and Hans-Peter Kriegel University of Munich, Germany Siemens Corporate.
A Coherent Locomotion Engine Extrapolating Beyond Experimental Data SCA ’ 04 Speaker: Alvin Data: January 3, 2005.
Mining Long Sequential Patterns in a Noisy Environment Jiong Yang, Wei Wang, Philip S. Yu, Jiawei Han SIGMOD 2002.
國中英文科教學活動設計 – 端午節 外文碩二 張維珊 外文碩二 聶欣瑩.
Jacinto C. Nascimento, Member, IEEE, and Jorge S. Marques
Robust Motion Watermarking based on Multiresolution Analysis EUROGRAPHICS 2000 Speaker: 彭任右, GAME Lab Date: 4/18/2005.
Segmenting Motion Capture Data into Distinct Behaviors Graphics Interface ‘ 04 Speaker: Alvin January 17, 2005.
Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models C. J. Leggetter and P. C. Woodland Department of.
Elec471 Embedded Computer Systems Chapter 4, Probability and Statistics By Prof. Tim Johnson, PE Wentworth Institute of Technology Boston, MA Theory and.
Intrusion and Anomaly Detection in Network Traffic Streams: Checking and Machine Learning Approaches ONR MURI area: High Confidence Real-Time Misuse and.
Introduction to Automatic Speech Recognition
Alignment and classification of time series gene expression in clinical studies Tien-ho Lin, Naftali Kaminski and Ziv Bar-Joseph.
Probabilistic Context Free Grammars for Representing Action Song Mao November 14, 2000.
Accelerating Statistical Static Timing Analysis Using Graphics Processing Units Kanupriya Gulati and Sunil P. Khatri Department of ECE, Texas A&M University,
Using Inactivity to Detect Unusual behavior Presenter : Siang Wang Advisor : Dr. Yen - Ting Chen Date : Motion and video Computing, WMVC.
Discovering Deformable Motifs in Time Series Data Jin Chen CSE Fall 1.
Processing Sequential Sensor Data The “John Krumm perspective” Thomas Plötz November 29 th, 2011.
LECTURE 3: ANALYSIS OF EXPERIMENTAL DATA
Published in: Computational Intelligence and Games (CIG), 2014 IEEE Conference on Author(s): Chong-u Lim Comput. Sci. & Artificial Intell. Lab., Massachusetts.
CS Statistical Machine learning Lecture 24
Variational Bayesian Methods for Audio Indexing
QUIZ!!  In HMMs...  T/F:... the emissions are hidden. FALSE  T/F:... observations are independent given no evidence. FALSE  T/F:... each variable X.
Inferring High-Level Behavior from Low-Level Sensors Donald J. Patterson, Lin Liao, Dieter Fox, and Henry Kautz.
Unsupervised Mining of Statistical Temporal Structures in Video Liu ze yuan May 15,2011.
Large-Scale Matrix Factorization with Missing Data under Additional Constraints Kaushik Mitra University of Maryland, College Park, MD Sameer Sheoreyy.
Week Aug-24 – Aug-29 Introduction to Spatial Computing CSE 5ISC Some slides adapted from the book Computing with Spatial Trajectories, Yu Zheng and Xiaofang.
ICA and PCA 學生:周節 教授:王聖智 教授. Outline Introduction PCA ICA Reference.
Phone-Level Pronunciation Scoring and Assessment for Interactive Language Learning Speech Communication, 2000 Authors: S. M. Witt, S. J. Young Presenter:
Kalman Filter and Data Streaming Presented By :- Ankur Jain Department of Computer Science 7/21/03.
Hierarchical Segmentation of Polarimetric SAR Images
Challenges in Creating an Automated Protein Structure Metaserver
Dynamical Statistical Shape Priors for Level Set Based Tracking
Easy Generation of Facial Animation Using Motion Graphs
Outline Texture modeling - continued Julesz ensemble.
CG Term Project Fragment-Based Image Completion
Nonparametric Bayesian Texture Learning and Synthesis
Auditory Morphing Weyni Clacken
Data-Driven Approach to Synthesizing Facial Animation Using Motion Capture Ioannis Fermanis Liu Zhaopeng
Presentation transcript:

Motion Texture: A Two-Level Statistical Model for Character Motion Synthesis SIGGRAPH ‘02 Speaker: Alvin Date: 3 August 2004

Alivn/GAME Lab./CSIE/NDHU 2 Outline Introduction Framework Result Conclusion Evaluation Form

Alivn/GAME Lab./CSIE/NDHU 3 Introduction Motion Texture – A two-level statistical model – Texton Local dynamics Represented by a linear dynamic system (LDS). – Distribution Global dynamics Modeled by a transition matrix – Counting how many times a texton is switched to another.

Alivn/GAME Lab./CSIE/NDHU 4 Two-level Statistical Model

Alivn/GAME Lab./CSIE/NDHU 5 Motion Texton State-Space model (LDS): X t – Hidden State Variable Y t – The Observation V t, W t – Independent Gaussian noises at time t.

Alivn/GAME Lab./CSIE/NDHU 6 Distribution Commonly used in HMMs

Alivn/GAME Lab./CSIE/NDHU 7 Introduction (cont.) Statistically similar to the original motion. Motion textures display a 1-D temporal distribution. User can synthesis and edit at both the texton level and the distribution level.

Alivn/GAME Lab./CSIE/NDHU 8 Framework Learning – E-step – M-step Synthesis – Texton Path Planning – Texton Synthesis By Sampling Noise With Constrained LDS

Alivn/GAME Lab./CSIE/NDHU 9 E-step Segment Labels as L = {l 1,l 2,…, l Ns } Segmentation points as H = {H 1,H 2,…,H Ns }

Alivn/GAME Lab./CSIE/NDHU 10 M-step

Alivn/GAME Lab./CSIE/NDHU 11 Learning Initialization - A greedy approach: Until the entire sequence is processed: – Use T min to fit LDS i – Label the subsequent frames to segment i until the fitting error is above a threshold. – Test all existing LDS’ to choose the best-fit LDS. – If no LDS fits well, introduce a new LDS.

Alivn/GAME Lab./CSIE/NDHU 12 Learning (cont.) The bigger the threshold, the longer the segments, and the fewer the number of textons. – Model selection methods: BIC MDL T min must be long enough to capture the local dynamics. – Approximately one second.

Alivn/GAME Lab./CSIE/NDHU 13 Texton Path Planning find a single best path,, which starts at and ends at. Two approaches: – Finding the Lowest Cost Path Dijkstra’s algorithm – Specifying the Path Length Dynamic Programming

Alivn/GAME Lab./CSIE/NDHU 14 Texton Synthesis By sampling noise – Inevitably depart from the original motion as time progresses. LDS learns only locally consistent motion patterns. The synthesis errors will accumulate as x t propagates. With constrained LDS – Setting the end constraints. – The in-between frames can be synthesized by solving a block-banded system of linear equations.

Alivn/GAME Lab./CSIE/NDHU 15 Result Environment – Intel P4 1.4G – 1G Memory Input – Capture 20 minutes of dance motion. (49800 frames) Result – It took about 4 hours to learn. – 246 textons are found. – The length of the texton ranges from 60 to 172 frames. – Synthesizing a texton only 25ms to 35ms. (Real-time)

Alivn/GAME Lab./CSIE/NDHU 16 Result (cont.)

Alivn/GAME Lab./CSIE/NDHU 17 Result (cont.)

Alivn/GAME Lab./CSIE/NDHU 18 Result (cont.)

Alivn/GAME Lab./CSIE/NDHU 19 Result (cont.)

Alivn/GAME Lab./CSIE/NDHU 20 Conclusion Best suited for repeated motions. Lack global variation when the data is limited. Did not incorporate any physical model into the synthesis algorithm. Capture the essential properties of the original motion.

Alivn/GAME Lab./CSIE/NDHU 21 Conclusion (cont.) The edited pose can not deviate from the original one too much. The additional constraint may contaminate the synthesized texton. Does not consider the interaction with environment. Initialization can be improved.

Alivn/GAME Lab./CSIE/NDHU 22 Evaluation Form 論文簡報部份 – 完整性介紹 (3) – 系統性介紹 (4) – 表達能力 (3) – 投影片製作 (3) 論文審閱部分 – 瞭解論文內容 (3) – 結果正確性與完整性 (4) – 原創性與重要性 (4) – 讀後啟發與應用: When we meet a problem that its input is highly repeating, we can use the statistical method to find the basic element.