13 th International Fall Workshop VISION, MODELING, AND VISUALIZATION 2008 October 8-10, 2008 Konstanz, Germany Strike a Pose Image-Based Pose Synthesis.

Slides:



Advertisements
Similar presentations
Pose Estimation and Segmentation of People in 3D Movies Karteek Alahari, Guillaume Seguin, Josef Sivic, Ivan Laptev Inria, Ecole Normale Superieure ICCV.
Advertisements

Recovering Human Body Configurations: Combining Segmentation and Recognition Greg Mori, Xiaofeng Ren, and Jitentendra Malik (UC Berkeley) Alexei A. Efros.
Character Animation from 2D Pictures and 3D Motion Data ACM Transactions on Graphics 2007.
- Recovering Human Body Configurations: Combining Segmentation and Recognition (CVPR’04) Greg Mori, Xiaofeng Ren, Alexei A. Efros and Jitendra Malik -
Image-based Clothes Animation for Virtual Fitting Zhenglong Zhou, Bo Shu, Shaojie Zhuo, Xiaoming Deng, Ping Tan, Stephen Lin * National University of.
Learning to estimate human pose with data driven belief propagation Gang Hua, Ming-Hsuan Yang, Ying Wu CVPR 05.
Modeling the Shape of People from 3D Range Scans
3/5/2002Phillip Saltzman Video Motion Capture Christoph Bregler Jitendra Malik UC Berkley 1997.
3DSkeleton-based Human Modeling with Metaballs 18 April 2008 Donghun Kim Robot Vision Lab.
International Conference on Automatic Face and Gesture Recognition, 2006 A Layered Deformable Model for Gait Analysis Haiping Lu, K.N. Plataniotis and.
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK.
Graph-Based Image Segmentation
Modeling 3D Deformable and Articulated Shapes Yu Chen, Tae-Kyun Kim, Roberto Cipolla Department of Engineering University of Cambridge.
PARAMETRIC RESHAPING OF HUMAN BODIES IN IMAGES SIGGRAPH 2010 Shizhe Zhou Hongbo Fu Ligang Liu Daniel Cohen-Or Xiaoguang Han.
Object Detection by Matching Longin Jan Latecki. Contour-based object detection Database shapes: …..
3D Game Programming All in One By Kenneth C. Finney.
1Notes  Questions?  Assignment 1 should be ready soon (will post to newsgroup as soon as it’s out)
Human Body Shape Estimation from Single Image Moin Nabi Computer Vision Lab. ©IPM - Dec
EE 7730 Image Segmentation.
Exchanging Faces in Images SIGGRAPH ’04 Blanz V., Scherbaum K., Vetter T., Seidel HP. Speaker: Alvin Date: 21 July 2004.
GATE D Object Representations (GATE-540) Dr.Çağatay ÜNDEĞER Instructor Middle East Technical University, GameTechnologies & General Manager SimBT.
Human Posture Recognition with Convex Programming Hao Jiang, Ze-Nian Li and Mark S. Drew School of Computing Science Simon Fraser University Burnaby, BC,
High-Quality Video View Interpolation
3D Hand Pose Estimation by Finding Appearance-Based Matches in a Large Database of Training Views
Texture Synthesis on Surfaces Paper by Greg Turk Presentation by Jon Super.
An Iterative Optimization Approach for Unified Image Segmentation and Matting Hello everyone, my name is Jue Wang, I’m glad to be here to present our paper.
Multi-camera Tracking of Articulated Human Motion using Motion and Shape Cues Aravind Sundaresan and Rama Chellappa Center for Automation Research University.
A Novel 2D To 3D Image Technique Based On Object- Oriented Conversion.
Adaptive Marching Cubes Renben Shu Chen Zhou Mohan S. Kankanhalli.
CSE554SimplificationSlide 1 CSE 554 Lecture 7: Simplification Fall 2014.
Input: Original intensity image. Target intensity image (i.e. a value sketch). Using Value Images to Adjust Intensity in 3D Renderings and Photographs.
A Scale and Rotation Invariant Approach to Tracking Human Body Part Regions in Videos Yihang BoHao Jiang Institute of Automation, CAS Boston College.
Introduction --Classification Shape ContourRegion Structural Syntactic Graph Tree Model-driven Data-driven Perimeter Compactness Eccentricity.
Marching Cubes: A High Resolution 3D Surface Construction Algorithm
Faking Dynamics of Cloth Animation for Animated Films Fabian Di Fiore Expertise Centre for Digital Media Hasselt University, Belgium
Computer Graphics Group Tobias Weyand Mesh-Based Inverse Kinematics Sumner et al 2005 presented by Tobias Weyand.
Niloy J. Mitra Leonidas J. Guibas Mark Pauly TU Vienna Stanford University ETH Zurich SIGGRAPH 2007.
Efficient Editing of Aged Object Textures By: Olivier Clément Jocelyn Benoit Eric Paquette Multimedia Lab.
Use and Re-use of Facial Motion Capture M. Sanchez, J. Edge, S. King and S. Maddock.
Graphite 2004 Statistical Synthesis of Facial Expressions for the Portrayal of Emotion Lisa Gralewski Bristol University United Kingdom
Automatic Visual Recognition of Armed Robbery particularly in convenience store settings.
Real-Time Animation of Realistic Virtual Humans. 1. The 3D virtual player is controlled by the real people who has a HMD and many sensors people who has.
NATIONAL TECHNICAL UNIVERSITY OF ATHENS Image, Video And Multimedia Systems Laboratory Background
S EGMENTATION FOR H ANDWRITTEN D OCUMENTS Omar Alaql Fab. 20, 2014.
Medical Imaging Dr. Mohammad Dawood Department of Computer Science University of Münster Germany.
Efficient Rendering of Local Subsurface Scattering Tom Mertens 1, Jan Kautz 2, Philippe Bekaert 1, Frank Van Reeth 1, Hans-Peter Seidel
Recognizing Action at a Distance Alexei A. Efros, Alexander C. Berg, Greg Mori, Jitendra Malik Computer Science Division, UC Berkeley Presented by Pundik.
Tracking People by Learning Their Appearance Deva Ramanan David A. Forsuth Andrew Zisserman.
Vision-based human motion analysis: An overview Computer Vision and Image Understanding(2007)
CSE554SimplificationSlide 1 CSE 554 Lecture 7: Simplification Fall 2013.
CSE554Fairing and simplificationSlide 1 CSE 554 Lecture 6: Fairing and Simplification Fall 2012.
AS-RIGID-AS-POSSIBLE SHAPE MANIPULATION
Mathematical Morphology Mathematical morphology (matematická morfologie) –A special image analysis discipline based on morphological transformations of.
Temporally Coherent Completion of Dynamic Shapes AUTHORS:HAO LI,LINJIE LUO,DANIEL VLASIC PIETER PEERS,JOVAN POPOVIC,MARK PAULY,SZYMON RUSINKIEWICZ Presenter:Zoomin(Zhuming)
High Resolution Surface Reconstruction from Overlapping Multiple-Views
Advisor : Ku-Yaw Chang Speaker : Ren-Li Shen /6/12.
Acquiring, Stitching and Blending Diffuse Appearance Attributes on 3D Models C. Rocchini, P. Cignoni, C. Montani, R. Scopigno Istituto Scienza e Tecnologia.
Image Representation and Description – Representation Schemes
Real-Time Human Pose Recognition in Parts from Single Depth Image
Iterative Optimization
Computer Animation and Visualisation Lecture 4. Skinning
“The Truth About Cats And Dogs”
Natural sciences 1.
Lecture 31: Graph-Based Image Segmentation
Easy Generation of Facial Animation Using Motion Graphs
Prepared by: Engr . Syed Atir Iftikhar
View synthesis aim to create new views of a specific subject by using two pictures taken from given point of views. Presented By: Shangchi Lin
Learning complex visual concepts
Presentation transcript:

13 th International Fall Workshop VISION, MODELING, AND VISUALIZATION 2008 October 8-10, 2008 Konstanz, Germany Strike a Pose Image-Based Pose Synthesis Cedric Vanaken, Chris Hermans, Tom Mertens, Fabian Di Fiore, Philippe Bekaert, Frank Van Reeth Hasselt University - Belgium

Image-Based Pose Synthesis Create novel poses from input images

Related Work As-Rigid-As-Possible Shape Manipulation [Igarashi et al.] Character Animation from 2D Pictures and 3D Motion Data [Hornung et al.] Video-Based Character Animation [Starck et al.] [Igarashi et al.] [Hornung et al.] [Starck et al.]

Related Work  standard image-based deformation: –Multiple input images (2 - 4) –Straightforward user-interaction Assign approximate skeleton –Higher realism in local regions e.g. creases in fabrics –Large variety of target poses If similar pose available in input

Algorithm Overview ? Skeleton Matching - Segmentation Target Skeleton

Algorithm Overview ? - Segmentation Skeleton Matching - Bodypart selection - Bodypart fusing Target Skeleton

2D Skeleton Matching ‘Articulated Video Sprites’ [Vanaken et al, 2006] (Absolute) positions of skeleton joints Angles  2D posture Limb Length Ratios  Implicit 3D information

Segmentation Background images available  Background subtraction Manual segmentation Semi-automatic –Grabcut [Rother et. al] –…

Body Part Selection Divide ‘body’ –Arms –Legs –Torso –Head For each body part - 2D skeleton matching - Keep best match If no unique best match - Keep all ‘good’ options - Combine in later stage

Mesh Creation Link skeleton with pixels Outer vertices  silhouette Inner vertices  Skeleton + edge image Mesh deformation  Larger variety for target poses

Pixel selection Link body parts with triangles Every triangle –‘confidently’ belongs to body part if Vertex on skeleton bone 2 closest skeleton bones belong to same body part –Otherwise ‘uncertain’ For each matching body part –Save ‘confident’ triangles to result –Fuse with ‘uncertain’ triangles

Fusing Body parts What we have until now : Fuse this into a nice result

Fusing Body parts Subdivide final image –Lattice of square patches For each patch –Find input patches matching ‘confident’ regions == Labeling problem For each patch, n input patches available (n == #overlapping ‘uncertain’ regions)

Fusing Body parts Cost function Data term –Patch overlap with ‘confident’ regions Smoothness term –Patch overlap with adjacent patches SSD Minimize function  Belief Propagation

Results Input 1Input 2Result Average of input 1 & input 2

Results Our method 2 input images Standard deformation 1 input image

Results

Starpulse Supermodels image gallery.

Overview Pose synthesis from set of photographs Merging body parts into desired pose User input : 2D skeletons

Future Work Automatic skeleton extraction Combine with animation/retargeting Occluding body parts Sideways capture 3D skeletons / multi-camera Color correction

Questions?