Face Poser: Interactive Modeling of 3D Facial Expressions Using Model Priors Manfred Lau 1,3 Jinxiang Chai 2 Ying-Qing Xu 3 Heung-Yeung Shum 3 1 Carnegie.

Slides:



Advertisements
Similar presentations
A Two-Step Approach to Hallucinating Faces: Global Parametric Model and Local Nonparametric Model Ce Liu Heung-Yeung Shum Chang Shui Zhang CVPR 2001.
Advertisements

CSCE643: Computer Vision Bayesian Tracking & Particle Filtering Jinxiang Chai Some slides from Stephen Roth.
CSE554Extrinsic DeformationsSlide 1 CSE 554 Lecture 10: Extrinsic Deformations Fall 2014.
Sami Romdhani Volker Blanz Thomas Vetter University of Freiburg
Face Alignment with Part-Based Modeling
1.  Texturing is a core process for modeling surface details in computer graphics applications › Texture mapping › Surface texture synthesis › Procedural.
Animation Following “Advanced Animation and Rendering Techniques” (chapter 15+16) By Agata Przybyszewska.
 INTRODUCTION  STEPS OF GESTURE RECOGNITION  TRACKING TECHNOLOGIES  SPEECH WITH GESTURE  APPLICATIONS.
1 Face Synthesis M. L. Gavrilova. 2 Outline Face Synthesis From Modeling to Synthesis Facial Expression Synthesis Conclusions.
Pseudo-Skeleton based ARAP Mesh Deformation M. Zollhöfer, A. Vieweg, J. Süßmuth and G. Greiner Computer Graphics Group, FAU Erlangen-Nuremberg, Germany.
SIGGRAPH Course 30: Performance-Driven Facial Animation For Latest Version of Bregler’s Slides and Notes please go to:
Lapped Textures Emil Praun and Adam Finkelstien (Princeton University) Huges Hoppe (Microsoft Research) SIGGRAPH 2000 Presented by Anteneh.
Summary & Homework Jinxiang Chai. Outline Motion data process paper summary Presentation tips Homework Paper assignment.
Introduction to Data-driven Animation Jinxiang Chai Computer Science and Engineering Texas A&M University.
Motion Editing and Retargetting Jinxiang Chai. Outline Motion editing [video, click here]here Motion retargeting [video, click here]here.
Iso-charts: Stretch-driven Mesh Parameterization using Spectral Analysis Kun Zhou, John Snyder*, Baining Guo, Heung-Yeung Shum Microsoft Research Asia.
CSCE 441 Computer Graphics: Keyframe Animation/Smooth Curves Jinxiang Chai.
Model-Based Stereo with Occlusions
Direct Methods for Visual Scene Reconstruction Paper by Richard Szeliski & Sing Bing Kang Presented by Kristin Branson November 7, 2002.
FiberMesh: Designing Freeform Surfaces with 3D Curves
Behavior Planning for Character Animation Manfred Lau and James Kuffner Carnegie Mellon University.
Constraint-based Motion Optimization Using A Statistical Dynamic Model Jinxiang Chai Texas A&M University.
Vision-based Control of 3D Facial Animation Jin-xiang Chai Jing Xiao Jessica Hodgins Carnegie Mellon University.
Siggraph’2000, July 27, 2000 Jin-Xiang Chai Xin Tong Shing-Chow Chan Heung-Yeung Shum Microsoft Research, China Plenoptic Sampling SIGGRAPH’2000.
Human Computer Interaction 7. Advanced User Interfaces (I) Data Scattering and RBF Course no. ILE5013 National Chiao Tung Univ, Taiwan By: I-Chen Lin,
Learning the Appearance of Faces: A Unifying Approach for the Analysis and Synthesis of Images. Thomas Vetter Germany University of Freiburg
Special Applications If we assume a specific application, many image- based rendering tools can be improved –The Lumigraph assumed the special domain of.
Radial Basis Function Networks
3D-Assisted Facial Texture Super-Resolution Pouria Mortazavian, Josef Kittler, William Christmas 10 September 2009 Centre for Vision, Speech and Signal.
Prediction of Non-Linear Aging Trajectories of Faces
Human Emotion Synthesis David Oziem, Lisa Gralewski, Neill Campbell, Colin Dalton, David Gibson, Barry Thomas University of Bristol, Motion Ripper, 3CR.
Motion Blending (Multidimensional Interpolation) Jehee Lee.
Computer Graphics Group Tobias Weyand Mesh-Based Inverse Kinematics Sumner et al 2005 presented by Tobias Weyand.
Irfan Essa, Alex Pentland Facial Expression Recognition using a Dynamic Model and Motion Energy (a review by Paul Fitzpatrick for 6.892)
“Graphical Modeling and Animation of Brittle Fracture” by James F. O’Brien and Jessica K. Hodgins, Georgia Institute of Technology “A Morphable Model.
Use and Re-use of Facial Motion Capture M. Sanchez, J. Edge, S. King and S. Maddock.
Facial animation retargeting framework using radial basis functions Tamás Umenhoffer, Balázs Tóth Introduction Realistic facial animation16 is a challenging.
Graphite 2004 Statistical Synthesis of Facial Expressions for the Portrayal of Emotion Lisa Gralewski Bristol University United Kingdom
Volumetric Illustration: Designing 3D Models with Internal Textures Shigeru Owada Frank Nielsen Makoto Okabe Takeo Igarashi The University of Tokyo Sony.
Light Using Texture Synthesis for Non-Photorealistic Shading from Paint Samples. Christopher D. Kulla, James D. Tucek, Reynold J. Bailey, Cindy M. Grimm.
Computer Graphics An Introduction. What’s this course all about? 06/10/2015 Lecture 1 2 We will cover… Graphics programming and algorithms Graphics data.
CS 638, Fall 2001 Today Project Stage 0.5 Environment mapping Light Mapping.
CS-378: Game Technology Lecture #4: Texture and Other Maps Prof. Okan Arikan University of Texas, Austin V Lecture #4: Texture and Other Maps.
Presented by Matthew Cook INFO410 & INFO350 S INFORMATION SCIENCE Paper Discussion: Dynamic 3D Avatar Creation from Hand-held Video Input Paper Discussion:
The Quotient Image: Class-based Recognition and Synthesis Under Varying Illumination T. Riklin-Raviv and A. Shashua Institute of Computer Science Hebrew.
Andrew Nealen / Olga Sorkine / Mark Alexa / Daniel Cohen-Or SoHyeon Jeong 2007/03/02.
AS-RIGID-AS-POSSIBLE SHAPE MANIPULATION
Lapped Solid Textrues Filling a Model with Anisotropic Textures
1 3D Screen-space Widgets for Non-linear Projection Patrick Coleman, Karan Singh (Univ of Toronto) Nisha Sudarsanam, Cindy Grimm (Washington Univ in St.
Intelligent Control and Automation, WCICA 2008.
- Laboratoire d'InfoRmatique en Image et Systèmes d'information
Categorization by Learning and Combing Object Parts B. Heisele, T. Serre, M. Pontil, T. Vetter, T. Poggio. Presented by Manish Jethwa.
CSCE 441 Computer Graphics: Keyframe Animation/Smooth Curves Jinxiang Chai.
3D Face Recognition Using Range Images
CSCE 441 Computer Graphics: Keyframe Animation/Smooth Curves Jinxiang Chai.
Skuller: A volumetric shape registration algorithm for modeling skull deformities Yusuf Sahillioğlu 1 and Ladislav Kavan 2 Medical Image Analysis 2015.
University of Washington v The Hebrew University * Microsoft Research Synthesizing Realistic Facial Expressions from Photographs Frederic Pighin Jamie.
Unsupervised Learning for Speech Motion Editing Eurographics/SIGGRAPH Symposium on Computer Animation (2003) Yong Cao 1,2 Petros Faloutsos 1 Frederic.
Application: Multiresolution Curves Jyun-Ming Chen Spring 2001.
Interactive Control of Avatars Animated with Human Motion Data By: Jehee Lee, Jinxiang Chai, Paul S. A. Reitsma, Jessica K. Hodgins, Nancy S. Pollard Presented.
Implicit Active Shape Models for 3D Segmentation in MR Imaging M. Rousson 1, N. Paragio s 2, R. Deriche 1 1 Odyssée Lab., INRIA Sophia Antipolis, France.
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
Face Recognition Summary –Single pose –Multiple pose –Principal components analysis –Model-based recognition –Neural Networks.
Image-Based Rendering Geometry and light interaction may be difficult and expensive to model –Think of how hard radiosity is –Imagine the complexity of.
3D Face Recognition Using Range Images Literature Survey Joonsoo Lee 3/10/05.
Morphing and Shape Processing
CSCE 441 Computer Graphics: Keyframe Animation/Smooth Curves
You can check broken videos in this slide here :
Sparse Rig Parameter Optimization for Character Animation
Occlusion and smoothness probabilities in 3D cluttered scenes
Presentation transcript:

Face Poser: Interactive Modeling of 3D Facial Expressions Using Model Priors Manfred Lau 1,3 Jinxiang Chai 2 Ying-Qing Xu 3 Heung-Yeung Shum 3 1 Carnegie Mellon University 2 Texas A&M University 3 Microsoft Research Asia

Face Poser Inputs Generate new facial expressions with a simple and intuitive interface

Face Poser InputsOutput Generate new facial expressions with a simple and intuitive interface

Why Face Poser? Pre-defined controls Difficult to build and use Complex facial expressions

Applications Films, GamesVirtual Reality Educational

Related Work Sketched-based interfaces Zeleznik et al. 96 Igarashi et al. 99 Nealen et al. 05 Kho and Garland 05 Chang and Jenkins 06 Nealen et al. 05 Igarashi et al. 99

Related Work Example-based modeling Blanz and Vetter 99 Pighin et al. 99 Chai et al. 03 Zhang et al. 04 Grochow et al. 04 Sumner et al. 05 Grochow et al. 04

Overview Database Preprocessing Model Prior

Overview Database Preprocessing Model Prior Neutral Pose User Constraints Interface

Overview Database Preprocessing Model Prior Runtime Optimization Neutral Pose New Pose User Constraints Interface Textured Pose

Motion capture data Captured mesh animations of various facial expressions: anger, fear, surprise, sadness, joy, disgust, speaking, singing All meshes translated and rotated to a standard view:

Data: PCA representation x = v 1x v 1y v 1z v 2x. p is low-dimensional representation of x

Problem statement Find best p satisfying user-constraints c: Best p is: Given a face model, how well does it match user-constraints Likelihood of face model using knowledge of data

Point Constraints More detailed control User inputs: blue – 3D source vertex green – 2D target pixel Can select in any camera view

Point Constraints We optimize for best p For each p: compute whole mesh x take selected 3D source vertex project it to 2D screen space compare to target pixel

Point Constraints Optimization term: Jacobian term:

Point Constraints InputsSolution

Point Constraints – Results

Point Constraints – Dragging interface

Stroke Constraints Large-scale changes with minimal input User inputs: blue – 2D source stroke (selects 3D points on mesh) green – 2D target stroke Any curve, line, or freeform region

Stroke Constraints 2D source stroke  raytrace each pixel to mesh surface to get dark gray points These can be 3D points on mesh surface (not just original mesh vertices)

Stroke Constraints We optimize for best p For each p: compute whole mesh x take selected 3D points project them to 2D screen space compare to target stroke

Stroke Constraints Optimization term: Jacobian term:

Stroke Constraints InputsSolution

Stroke Constraints – Results

Stroke Constraints – Tablet interface

Stroke Constraints – Additional term If strokes are far away from each other, energy term will reach local minimum Need additional optimization term to minimize distance between “center” of source stroke and “center” of target stroke Without additional term

Stroke Constraints – Additional term Without additional term Optimization term: Jacobian term:

Stroke Constraints – Additional term Without additional termWith additional term

Stroke Constraints – Results

Problem statement Find best p satisfying user-constraints c: Best p is: Given a face model, how well does it match user-constraints Likelihood of face model using knowledge of data

Model Priors There can be many solutions satisfying user constraints. Some of them are not realistic. We add another optimization term to constrain the solution to the space defined by the motion capture data. Without model priors term

Model Priors Without model priors term Learn a Mixtures of Factor Analyzers (MFA) model Probability density function to measure naturalness of facial expression MFA has been applied to high-dimensional nonlinear data

Model Priors Without model priors term Optimization term: Jacobian term:

Model Priors – Result

increasing weight on Model Prior term

Model Priors – Result

Computation time Standard PC hardware (Pentium IV 2 GHz) Point constraints takes 0.18 seconds for 10 points time increases linearly with number of points Stroke constraints takes 0.4 seconds for source stroke of ~900 pixels (about size of eyebrow) time increases linearly with number of pixels faster if using intermediate spline representation

Cross validation New face expression samples for testing Use new samples to get target constraints Generate solution and compare with test sample

Cross validation Ground truth Interpolation Optimization

Comparison with other techniques Opt-blend: FaceIK [Zhang et al. 04] PCA: Morphable model [Blanz and Vetter 99; Blanz et al. 03] LWR: Locally weighted regression 3D errors

Comparison with other techniques Ground truth, Optimization with PCA, Optimization with MFA

Application: Trajectory Keyframing Green points – given 2D target pixels Blue points and mesh – solution

Application: Trajectory Keyframing Ground truth Result

Application: Trajectory Keyframing Ground truth Result

Application: Trajectory Keyframing Ground truth Result

Summary: Face Poser InputsOutput Users can learn to use our system within minutes and can create new facial expressions within seconds

Limitation Global control  changing mouth also changes eyes  this is natural, but difficult to control sometimes Local control  changing mouth without changing eyes  but this might lead to “fake smiles”

Extensions / Future work We have added different types of constraints within the same optimization framework More general: model face as separate regions, generate each region separately, and blend them back together