3D Face Modeling. Lacey Best- Rowden, Joseph Roth Feb. 18, MSU
|
|
- Beverly Warner
- 6 years ago
- Views:
Transcription
1 3D Face Modeling Lacey Best- Rowden, Joseph Roth Feb. 18, MSU
2 Outline ApplicaDon / Benefits 3D ReconstrucDon Techniques o Range Scanners o Single Image! 3DMM o MulDple Image! Shape from stereo! Photometric stereo! Shape from modon Conclusion
3 ApplicaDons/Benefits to FR Invariant to o IlluminaDon o Pose o Background Allows o Warping to frontal o ParDal matching
4 Challenges Non- rigid object Dense landmark detecdon Require user cooperadon for range scanners o Minolta Vivid 900: 2.5sec
5 RepresentaDon Depth map Point cloud Mesh
6 ReconstrucDon Direct Acquisi,on Single Image MulDple Images
7 Range Scanners Bounce waves off subject and measure reflecdon Requires user to be stadonary Post processing to fill holes / remove outliers
8 Structured Light Shine pa]ern on object Measure warping of pa]ern
9 ReconstrucDon Direct AcquisiDon Single Image MulDple Images
10 3D Morphable Model A generadve model Linear 3D shape and appearance model + imaging model Maps 3D surface onto an image Classic works: V. Blanz and T. Ve]er. Face RecogniDon Based on Fi`ng a 3D Morphable Model. PAMI, V. Blanz and T. Ve]er. A Morphable Model for the Synthesis of 3D Faces. SIGGRAPH, 1999.
11 3D Morphable Model Vector representadons of geometry and texture of 3D face ( ) T R 3n ( ) T R 3n S = X 1,Y 1,Z 1,X 2,,Y n,z n T = R 1,G 1,B 1,R 2,,G n,b n New shapes and new textures from m exemplar/prototypical faces in full correspondence S mod = m a i S i T mod = b i T i i=1 The morphable model is a set of faces parameterized by coefficients S mod ( a! ),T mod ( b! ) ( ) m i=1 m m a i = b i =1 i=1 i=1!! a = ( a 1,a 2,,a m ) T b = ( b 1,b 2,,b m ) T Arbitrary new faces can be generated by varying the shape!! and texture coefficients, a and b
12 3D Morphable Model: PCA Linear combinadons can contain non- faces Coefficient vectors need assigned probabilides of describing a face PCA on shape and texture vectors of the set of m exemplar 3D faces Instead of describing a novel shape and texture as a linear combinadon of example faces, linear combinadons of N S shape and N T texture principal components N S S = S + α i S i T = T + β i T i i=1 N T i=1
13 3D Morphable Model: PCA
14 3D Morphable Model: Segments 200 example faces Dimensionality of shape and texture spaces are limited Need more 3D scans Larger variety of faces if linear combinadons of shape and texture are formed separately for different regions MulDplies dimensionality of MM by four Image blending technique used to smooth the transidons between segments
15 Building a Morphable Model Database of 3D laser head scans 100 males, 100 females Mostly Caucasian Key problem: need a dense point- to- point correspondence between verdces of 3D faces Mesh- based algorithms Non- rigid IteraDve Closest Point (ICP)
16 Correspondence via Non- Rigid ICP Progressively deforms a template/reference face towards the measured surface Starts with a strong regularizadon First recovers global deformadons RegularizaDon is then lowered Allows progressively more local deformadons
17 Model- Based Image Analysis Represent a novel face in an image by model coefficients and provide a reconstrucdon of 3D shape AutomaDcally esdmates all rendering/scene parameters Analysis: model inversion problem? StochasDc Newton OpDmizaDon updates/iteradons based on 1 st and 2 nd derivadves of a MAP energy funcdon Synthesis: generadon of accurate face images Viewed under any possible rendering condidons (pose, illuminadon, expression, etc.)
18 Model- Based Image Analysis: FiEng
19 Model- Based Image Analysis: FiEng Minimize the sum of squared errors over all color channels and pixels between the image and the reconstrucdon E I = I input (x, y) I model (x, y) x,y q x, j E F = I input I q model j y, j p x,k j p y,k j MinimizaDon may cause overfi`ng 2 2 First iteradons exploit manually defined feature points ( 8) Maximum a posteriori (MAP) esdmadon of the parameters
20 Model- Based Image Analysis: MAP Find model parameters with maximum posterior probability. Bayes Rule, p α,β,ρ I input,f Assume independence, p α,β,ρ I input,f ( )P α,β,ρ ( ) ~ p I input,f α,β,ρ ( ) p F α,β,ρ ( ) ~ p I input α,β,ρ Priors of shape and texture esdmated with PCA Assume normal distribudon of rendering parameters ( ) ~ exp 1 p I input α,β,ρ 2 2σ E I I Posterior maximized by minimizing cost funcdon StochasDc Newton OpDmizaDon (SNO) algorithm ( ) ( )P( α)p( β)p ρ ( ) ~ exp 1 p F α,β,ρ E = 2 log p( α,β,ρ I input,f) ( ) 2 2σ E F F
21 Fi`ng Results (SNO)
22 Many FiEng Algorithms AcDve Shape Model (ASM) AcDve Appearance Model (AAM) Inverse ComposiDonal Image Alignment (ICIA) ICIA applied to 3DMM MulD- Features Fi`ng (MFF) 2D+3D AAM Linear Shape and Texture fi`ng
23 Face Recogni,on Paradigms RecogniDon based on nearest- neighbor of model coefficients Intrinsic shape and texture of faces Independent of imaging condidons SyntheDc views of gallery or probe images Pose correcdon to frontal Generate views at various poses
24 Recogni,on Results FERET database CMU- PIE database
25 Recogni,on Results
26 Recogni,on Results
27 NIST FRVT 2002: Morphable Models Results Gallery: 87 subjects (frontal, controlled) Probe: 87 images of 87 subjects (9 sets)
28 FRVT 2002: Morphable Models Results
29 ReconstrucDon Direct AcquisiDon Single Image Mul,ple Images
30 Shape from Stereo 2 cameras with known posidon Measure disparity between corresponding points
31 Photometric Stereo Single camera MulDple images with different light sources Why does this work?
32 Photometric Stereo Unknown lighdng Decompose into light and shape images pixels M nxp M = LS - L nx4, S 4xp - S i = [p, p*n x, p*n y, p*n z ] T
33 ReconstrucDng Faces 1. EsDmate pose and warp to near frontal 2. Solve inidal lighdng and shape 3. Refine shape via local patches 4. Integrate shape 5. Repeat with updated template
34 Pose EsDmaDon q = srq+t q: 2D landmarks in photo Q: 3D landmarks in template s: scale R: rotadon t: transladon
35 Expression NormalizaDon Low rank approximadon to get shape also removes expression from images Preserves lighdng
36 Results Can you guess who these people are?
37 Shape from MoDon MoDon of object MoDon of camera EsDmate geometry and modon simultaneously
38 The End Any QuesDons?
39 References [1] I. Kemelmacher- Shlizerman and S. Seitz. Face ReconstrucDon in the Wild. ICCV [2] V. Blanz and T. Ve]er. Face RecogniDon Based on Fi`ng a 3D Morphable Model. PAMI, [3] V. Blanz and T. Ve]er. A Morphable Model for the Synthesis of 3D Faces. SIGGRAPH, 1999.
IMAGE-BASED MODELING & RENDERING (1)
CS580: Computer Graphics KAIST School of CompuDng IMAGE-BASED MODELING & RENDERING (1) Some next lecture slides are adopted from slides of Prof. Ravi Ramamoorthi (USCD), Marc Levoy (Google), Michael Cohen
More informationFace Recognition Markus Storer, 2007
Face Recognition Markus Storer, 2007 Agenda Face recognition by humans 3D morphable models pose and illumination model creation model fitting results Face recognition vendor test 2006 Face Recognition
More informationFace Recognition At-a-Distance Based on Sparse-Stereo Reconstruction
Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction Ham Rara, Shireen Elhabian, Asem Ali University of Louisville Louisville, KY {hmrara01,syelha01,amali003}@louisville.edu Mike Miller,
More informationFace Alignment Across Large Poses: A 3D Solution
Face Alignment Across Large Poses: A 3D Solution Outline Face Alignment Related Works 3D Morphable Model Projected Normalized Coordinate Code Network Structure 3D Image Rotation Performance on Datasets
More informationRegistration of Expressions Data using a 3D Morphable Model
Registration of Expressions Data using a 3D Morphable Model Curzio Basso, Pascal Paysan, Thomas Vetter Computer Science Department, University of Basel {curzio.basso,pascal.paysan,thomas.vetter}@unibas.ch
More informationFaces. Face Modeling. Topics in Image-Based Modeling and Rendering CSE291 J00 Lecture 17
Face Modeling Topics in Image-Based Modeling and Rendering CSE291 J00 Lecture 17 Faces CS291-J00, Winter 2003 From David Romdhani Kriegman, slides 2003 1 Approaches 2-D Models morphing, indexing, etc.
More information3D Face Recognition. Anil K. Jain. Dept. of Computer Science & Engineering Michigan State University.
3D Face Recognition Anil K. Jain Dept. of Computer Science & Engineering Michigan State University http://biometrics.cse.msu.edu Face Recognition 1959? 1960 1972 1973 Face detection using OpenCV Viola-Jones
More information22 October, 2012 MVA ENS Cachan. Lecture 5: Introduction to generative models Iasonas Kokkinos
Machine Learning for Computer Vision 1 22 October, 2012 MVA ENS Cachan Lecture 5: Introduction to generative models Iasonas Kokkinos Iasonas.kokkinos@ecp.fr Center for Visual Computing Ecole Centrale Paris
More information3D Face Modelling Under Unconstrained Pose & Illumination
David Bryan Ottawa-Carleton Institute for Biomedical Engineering Department of Systems and Computer Engineering Carleton University January 12, 2009 Agenda Problem Overview 3D Morphable Model Fitting Model
More informationData-driven Methods: Faces. Portrait of Piotr Gibas Joaquin Rosales Gomez (2003)
Data-driven Methods: Faces Portrait of Piotr Gibas Joaquin Rosales Gomez (2003) CS194: Image Manipulation & Computational Photography Alexei Efros, UC Berkeley, Fall 2016 The Power of Averaging 8-hour
More informationImage Morphing. Application: Movie Special Effects. Application: Registration /Alignment. Image Cross-Dissolve
Image Morphing Application: Movie Special Effects Morphing is turning one image into another (through a seamless transition) First movies with morphing Willow, 1988 Indiana Jones and the Last Crusade,
More informationFace Recognition based on a 3D Morphable Model
Face Recognition based on a 3D Morphable Model Volker Blanz University of Siegen Hölderlinstr. 3 57068 Siegen, Germany blanz@informatik.uni-siegen.de Abstract This paper summarizes the main concepts of
More informationCorrespondence. CS 468 Geometry Processing Algorithms. Maks Ovsjanikov
Shape Matching & Correspondence CS 468 Geometry Processing Algorithms Maks Ovsjanikov Wednesday, October 27 th 2010 Overall Goal Given two shapes, find correspondences between them. Overall Goal Given
More informationMulti-View AAM Fitting and Camera Calibration
To appear in the IEEE International Conference on Computer Vision Multi-View AAM Fitting and Camera Calibration Seth Koterba, Simon Baker, Iain Matthews, Changbo Hu, Jing Xiao, Jeffrey Cohn, and Takeo
More informationRegistration of Dynamic Range Images
Registration of Dynamic Range Images Tan-Chi Ho 1,2 Jung-Hong Chuang 1 Wen-Wei Lin 2 Song-Sun Lin 2 1 Department of Computer Science National Chiao-Tung University 2 Department of Applied Mathematics National
More informationSurface Registration. Gianpaolo Palma
Surface Registration Gianpaolo Palma The problem 3D scanning generates multiple range images Each contain 3D points for different parts of the model in the local coordinates of the scanner Find a rigid
More informationState of The Art In 3D Face Recognition
State of The Art In 3D Face Recognition Index 1 FROM 2D TO 3D 3 2 SHORT BACKGROUND 4 2.1 THE MOST INTERESTING 3D RECOGNITION SYSTEMS 4 2.1.1 FACE RECOGNITION USING RANGE IMAGES [1] 4 2.1.2 FACE RECOGNITION
More informationFace View Synthesis Across Large Angles
Face View Synthesis Across Large Angles Jiang Ni and Henry Schneiderman Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 1513, USA Abstract. Pose variations, especially large out-of-plane
More informationStructured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov
Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter
More informationFace Recognition Based on Frontal Views Generated from Non-Frontal Images
Face Recognition Based on Frontal Views Generated from Non-Frontal Images Volker Blanz 1, Patrick Grother 2, P. Jonathon Phillips 2 and Thomas Vetter 3 1 Max-Planck-Institut für Informatik, Saarbrücken,
More information3D Active Appearance Model for Aligning Faces in 2D Images
3D Active Appearance Model for Aligning Faces in 2D Images Chun-Wei Chen and Chieh-Chih Wang Abstract Perceiving human faces is one of the most important functions for human robot interaction. The active
More informationRobust Human Body Shape and Pose Tracking
Robust Human Body Shape and Pose Tracking Chun-Hao Huang 1 Edmond Boyer 2 Slobodan Ilic 1 1 Technische Universität München 2 INRIA Grenoble Rhône-Alpes Marker-based motion capture (mocap.) Adventages:
More informationNonrigid Surface Modelling. and Fast Recovery. Department of Computer Science and Engineering. Committee: Prof. Leo J. Jia and Prof. K. H.
Nonrigid Surface Modelling and Fast Recovery Zhu Jianke Supervisor: Prof. Michael R. Lyu Committee: Prof. Leo J. Jia and Prof. K. H. Wong Department of Computer Science and Engineering May 11, 2007 1 2
More informationFitting a Single Active Appearance Model Simultaneously to Multiple Images
Fitting a Single Active Appearance Model Simultaneously to Multiple Images Changbo Hu, Jing Xiao, Iain Matthews, Simon Baker, Jeff Cohn, and Takeo Kanade The Robotics Institute, Carnegie Mellon University
More informationRobotics Programming Laboratory
Chair of Software Engineering Robotics Programming Laboratory Bertrand Meyer Jiwon Shin Lecture 8: Robot Perception Perception http://pascallin.ecs.soton.ac.uk/challenges/voc/databases.html#caltech car
More informationStereo vision. Many slides adapted from Steve Seitz
Stereo vision Many slides adapted from Steve Seitz What is stereo vision? Generic problem formulation: given several images of the same object or scene, compute a representation of its 3D shape What is
More informationA 3D Face Model for Pose and Illumination Invariant Face Recognition
A 3D Face Model for Pose and Illumination Invariant Face Recognition Pascal Paysan Reinhard Knothe Brian Amberg pascal.paysan@unibas.ch reinhard.knothe@unibas.ch brian.amberg@unibas.ch Sami Romdhani Thomas
More informationDense 3D Modelling and Monocular Reconstruction of Deformable Objects
Dense 3D Modelling and Monocular Reconstruction of Deformable Objects Anastasios (Tassos) Roussos Lecturer in Computer Science, University of Exeter Research Associate, Imperial College London Overview
More informationExpression Invariant 3D Face Recognition with a Morphable Model
Expression Invariant 3D Face Recognition with a Morphable Model Brian Amberg brian.amberg@unibas.ch Reinhard Knothe reinhard.knothe@unibas.ch Thomas Vetter thomas.vetter@unibas.ch Abstract We describe
More information3D Computer Vision. Depth Cameras. Prof. Didier Stricker. Oliver Wasenmüller
3D Computer Vision Depth Cameras Prof. Didier Stricker Oliver Wasenmüller Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de
More information3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.
3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction
More informationA Morphable Model for the Synthesis of 3D Faces
A Morphable Model for the Synthesis of 3D Faces Marco Nef Volker Blanz, Thomas Vetter SIGGRAPH 99, Los Angeles Presentation overview Motivation Introduction Database Morphable 3D Face Model Matching a
More informationReconstruction and Recognition of 3D Face Models MSc Report
Reconstruction and Recognition of 3D Face Models MSc Report Name: Oisín Mac Aodha Supervisor: Dr. Simon Prince Year of Submission: 2007/08 Programme: MSc Intelligent Systems Disclaimer: This report is
More informationProcessing 3D Surface Data
Processing 3D Surface Data Computer Animation and Visualisation Lecture 17 Institute for Perception, Action & Behaviour School of Informatics 3D Surfaces 1 3D surface data... where from? Iso-surfacing
More informationFace Modeling. Portrait of Piotr Gibas Joaquin Rosales Gomez
Face Modeling Portrait of Piotr Gibas Joaquin Rosales Gomez 15-463: Computational Photography Alexei Efros, CMU, Fall 2006 The Power of Averaging Figure-centric averages Antonio Torralba & Aude Oliva (2002)
More informationRobust AAM Fitting by Fusion of Images and Disparity Data
IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, June 17-22, 2006, Vol. 2, pp.2483-2490 Robust AAM Fitting by Fusion of Images and Disparity Data Joerg Liebelt
More informationBIL Computer Vision Apr 16, 2014
BIL 719 - Computer Vision Apr 16, 2014 Binocular Stereo (cont d.), Structure from Motion Aykut Erdem Dept. of Computer Engineering Hacettepe University Slide credit: S. Lazebnik Basic stereo matching algorithm
More informationDense 3D Reconstruction. Christiano Gava
Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Today: dense 3D reconstruction The matching problem
More informationMiniature faking. In close-up photo, the depth of field is limited.
Miniature faking In close-up photo, the depth of field is limited. http://en.wikipedia.org/wiki/file:jodhpur_tilt_shift.jpg Miniature faking Miniature faking http://en.wikipedia.org/wiki/file:oregon_state_beavers_tilt-shift_miniature_greg_keene.jpg
More information5LSH0 Advanced Topics Video & Analysis
1 Multiview 3D video / Outline 2 Advanced Topics Multimedia Video (5LSH0), Module 02 3D Geometry, 3D Multiview Video Coding & Rendering Peter H.N. de With, Sveta Zinger & Y. Morvan ( p.h.n.de.with@tue.nl
More informationProcessing 3D Surface Data
Processing 3D Surface Data Computer Animation and Visualisation Lecture 12 Institute for Perception, Action & Behaviour School of Informatics 3D Surfaces 1 3D surface data... where from? Iso-surfacing
More informationSynthesizing Realistic Facial Expressions from Photographs
Synthesizing Realistic Facial Expressions from Photographs 1998 F. Pighin, J Hecker, D. Lischinskiy, R. Szeliskiz and D. H. Salesin University of Washington, The Hebrew University Microsoft Research 1
More informationGeometric Registration for Deformable Shapes 1.1 Introduction
Geometric Registration for Deformable Shapes 1.1 Introduction Overview Data Sources and Applications Problem Statement Overview Presenters Will Chang University of California at San Diego, USA Hao Li ETH
More informationC280, Computer Vision
C280, Computer Vision Prof. Trevor Darrell trevor@eecs.berkeley.edu Lecture 11: Structure from Motion Roadmap Previous: Image formation, filtering, local features, (Texture) Tues: Feature-based Alignment
More informationEE795: Computer Vision and Intelligent Systems
EE795: Computer Vision and Intelligent Systems Spring 2012 TTh 17:30-18:45 FDH 204 Lecture 10 130221 http://www.ee.unlv.edu/~b1morris/ecg795/ 2 Outline Review Canny Edge Detector Hough Transform Feature-Based
More informationNew Experiments on ICP-Based 3D Face Recognition and Authentication
New Experiments on ICP-Based 3D Face Recognition and Authentication Boulbaba Ben Amor Boulbaba.Ben-Amor@ec-lyon.fr Liming Chen Liming.Chen@ec-lyon.fr Mohsen Ardabilian Mohsen.Ardabilian@ec-lyon.fr Abstract
More informationImage Transfer Methods. Satya Prakash Mallick Jan 28 th, 2003
Image Transfer Methods Satya Prakash Mallick Jan 28 th, 2003 Objective Given two or more images of the same scene, the objective is to synthesize a novel view of the scene from a view point where there
More informationMulti-view stereo. Many slides adapted from S. Seitz
Multi-view stereo Many slides adapted from S. Seitz Beyond two-view stereo The third eye can be used for verification Multiple-baseline stereo Pick a reference image, and slide the corresponding window
More informationLearning a generic 3D face model from 2D image databases using incremental structure from motion
Learning a generic 3D face model from 2D image databases using incremental structure from motion Jose Gonzalez-Mora 1,, Fernando De la Torre b, Nicolas Guil 1,, Emilio L. Zapata 1 a Department of Computer
More informationFace Recognition Across Poses Using A Single 3D Reference Model
2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops Face Recognition Across Poses Using A Single 3D Reference Model Gee-Sern Hsu, Hsiao-Chia Peng National Taiwan University of Science
More informationLearning and Inferring Depth from Monocular Images. Jiyan Pan April 1, 2009
Learning and Inferring Depth from Monocular Images Jiyan Pan April 1, 2009 Traditional ways of inferring depth Binocular disparity Structure from motion Defocus Given a single monocular image, how to infer
More informationRealistic Texture Extraction for 3D Face Models Robust to Self-Occlusion
Realistic Texture Extraction for 3D Face Models Robust to Self-Occlusion Chengchao Qu 1,2 Eduardo Monari 2 Tobias Schuchert 2 Jürgen Beyerer 2,1 1 Vision and Fusion Laboratory, Karlsruhe Institute of Technology
More informationAAM Based Facial Feature Tracking with Kinect
BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 15, No 3 Sofia 2015 Print ISSN: 1311-9702; Online ISSN: 1314-4081 DOI: 10.1515/cait-2015-0046 AAM Based Facial Feature Tracking
More informationTEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA
TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA Tomoki Hayashi 1, Francois de Sorbier 1 and Hideo Saito 1 1 Graduate School of Science and Technology, Keio University, 3-14-1 Hiyoshi,
More informationSlides modified from: PATTERN RECOGNITION AND MACHINE LEARNING CHRISTOPHER M. BISHOP
Slides modified from: PATTERN RECOGNITION AND MACHINE LEARNING CHRISTOPHER M. BISHOP Linear regression Linear Basis FuncDon Models (1) Example: Polynomial Curve FiLng Linear Basis FuncDon Models (2) Generally
More informationDense 3D Reconstruction. Christiano Gava
Dense 3D Reconstruction Christiano Gava christiano.gava@dfki.de Outline Previous lecture: structure and motion II Structure and motion loop Triangulation Wide baseline matching (SIFT) Today: dense 3D reconstruction
More information2D + 3D FACE MORPHING 1 Yen-Cheng Liu ( ) 2 Pei-Hwai Ciou ( ) Chiou-Shann Fuh ( )
2D + 3D FACE MORPHING 1 Yen-Cheng Liu ( ) 2 Pei-Hwai Ciou ( ) Chiou-Shann Fuh ( ) 1, 2 Graduate Institute of Electrical Engineering National Taiwan University Taipei, Taiwan r49213@ntu.edu.tw r49218@ntu.edu.tw
More information3D Human Motion Analysis and Manifolds
D E P A R T M E N T O F C O M P U T E R S C I E N C E U N I V E R S I T Y O F C O P E N H A G E N 3D Human Motion Analysis and Manifolds Kim Steenstrup Pedersen DIKU Image group and E-Science center Motivation
More informationA novel 3D torso image reconstruction procedure using a pair of digital stereo back images
Modelling in Medicine and Biology VIII 257 A novel 3D torso image reconstruction procedure using a pair of digital stereo back images A. Kumar & N. Durdle Department of Electrical & Computer Engineering,
More informationFace Re-Lighting from a Single Image under Harsh Lighting Conditions
Face Re-Lighting from a Single Image under Harsh Lighting Conditions Yang Wang 1, Zicheng Liu 2, Gang Hua 3, Zhen Wen 4, Zhengyou Zhang 2, Dimitris Samaras 5 1 The Robotics Institute, Carnegie Mellon University,
More informationInput. Output. Problem Definition. Rectified stereo image pair All correspondences lie in same scan lines
Problem Definition 3 Input Rectified stereo image pair All correspondences lie in same scan lines Output Disparity map of the reference view Foreground: large disparity Background: small disparity Matching
More informationIntegrating Range and Texture Information for 3D Face Recognition
Integrating Range and Texture Information for 3D Face Recognition Xiaoguang Lu and Anil K. Jain Dept. of Computer Science & Engineering Michigan State University East Lansing, MI 48824 {Lvxiaogu, jain}@cse.msu.edu
More informationSupplementary Material for Synthesizing Normalized Faces from Facial Identity Features
Supplementary Material for Synthesizing Normalized Faces from Facial Identity Features Forrester Cole 1 David Belanger 1,2 Dilip Krishnan 1 Aaron Sarna 1 Inbar Mosseri 1 William T. Freeman 1,3 1 Google,
More informationA Framework for Long Distance Face Recognition using Dense- and Sparse-Stereo Reconstruction
A Framework for Long Distance Face Recognition using Dense- and Sparse-Stereo Reconstruction Ham Rara, Shireen Elhabian, Asem Ali, Travis Gault, Mike Miller, Thomas Starr, and Aly Farag CVIP Laboratory,
More informationMulti-View Stereo for Static and Dynamic Scenes
Multi-View Stereo for Static and Dynamic Scenes Wolfgang Burgard Jan 6, 2010 Main references Yasutaka Furukawa and Jean Ponce, Accurate, Dense and Robust Multi-View Stereopsis, 2007 C.L. Zitnick, S.B.
More informationLecture 7: Image Morphing. Idea #2: Align, then cross-disolve. Dog Averaging. Averaging vectors. Idea #1: Cross-Dissolving / Cross-fading
Lecture 7: Image Morphing Averaging vectors v = p + α (q p) = (1 - α) p + α q where α = q - v p α v (1-α) q p and q can be anything: points on a plane (2D) or in space (3D) Colors in RGB or HSV (3D) Whole
More informationLecture 20: Tracking. Tuesday, Nov 27
Lecture 20: Tracking Tuesday, Nov 27 Paper reviews Thorough summary in your own words Main contribution Strengths? Weaknesses? How convincing are the experiments? Suggestions to improve them? Extensions?
More informationData-driven Methods: Faces. Portrait of Piotr Gibas Joaquin Rosales Gomez
Data-driven Methods: Faces Portrait of Piotr Gibas Joaquin Rosales Gomez 15-463: Computational Photography Alexei Efros, CMU, Fall 2010 The Power of Averaging 8-hour exposure Atta Kim Fun with long exposures
More informationMonocular Head Pose Es0ma0on
ICIAR 2008 - Interna0onal Conference on Image Analysis and Recogni0on Monocular Head Pose Es0ma0on Pedro Mar0ns, Jorge Ba0sta Ins0tute for Systems and Robo0cs h>p://www.isr.uc.pt Department of Electrical
More informationFaces and Image-Based Lighting
Announcements Faces and Image-Based Lighting Project #3 artifacts voting Final project: Demo on 6/25 (Wednesday) 13:30pm in this room Reports and videos due on 6/26 (Thursday) 11:59pm Digital Visual Effects,
More informationOn the Dimensionality of Deformable Face Models
On the Dimensionality of Deformable Face Models CMU-RI-TR-06-12 Iain Matthews, Jing Xiao, and Simon Baker The Robotics Institute Carnegie Mellon University 5000 Forbes Avenue Pittsburgh, PA 15213 Abstract
More information3D Morphable Model Parameter Estimation
3D Morphable Model Parameter Estimation Nathan Faggian 1, Andrew P. Paplinski 1, and Jamie Sherrah 2 1 Monash University, Australia, Faculty of Information Technology, Clayton 2 Clarity Visual Intelligence,
More informationImage Stitching. Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi
Image Stitching Slides from Rick Szeliski, Steve Seitz, Derek Hoiem, Ira Kemelmacher, Ali Farhadi Combine two or more overlapping images to make one larger image Add example Slide credit: Vaibhav Vaish
More informationA consumer level 3D object scanning device using Kinect for web-based C2C business
A consumer level 3D object scanning device using Kinect for web-based C2C business Geoffrey Poon, Yu Yin Yeung and Wai-Man Pang Caritas Institute of Higher Education Introduction Internet shopping is popular
More informationGeometric Registration for Deformable Shapes 2.2 Deformable Registration
Geometric Registration or Deormable Shapes 2.2 Deormable Registration Variational Model Deormable ICP Variational Model What is deormable shape matching? Example? What are the Correspondences? Eurographics
More informationFACIAL ANIMATION FROM SEVERAL IMAGES
International Archives of Photogrammetry and Remote Sensing. Vol. XXXII, Part 5. Hakodate 1998 FACIAL ANIMATION FROM SEVERAL IMAGES Yasuhiro MUKAIGAWAt Yuichi NAKAMURA+ Yuichi OHTA+ t Department of Information
More informationSelf-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material
Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material Ayush Tewari 1,2 Michael Zollhöfer 1,2,3 Pablo Garrido 1,2 Florian Bernard 1,2 Hyeongwoo
More informationActive motion compensation for cardiac surgery
Active motion compensation for cardiac surgery Prof. Dr. Ing. Philippe POIGNET LIRMM UMR 5506 CNRS - University of Montpellier RoboDcs Department, France poignet@lirmm.fr BioDev 14 LIRMM / Robo)cs Dpt
More informationUnderstanding Faces. Detection, Recognition, and. Transformation of Faces 12/5/17
Understanding Faces Detection, Recognition, and 12/5/17 Transformation of Faces Lucas by Chuck Close Chuck Close, self portrait Some slides from Amin Sadeghi, Lana Lazebnik, Silvio Savarese, Fei-Fei Li
More informationIn Between 3D Active Appearance Models and 3D Morphable Models
In Between 3D Active Appearance Models and 3D Morphable Models Jingu Heo and Marios Savvides Biometrics Lab, CyLab Carnegie Mellon University Pittsburgh, PA 15213 jheo@cmu.edu, msavvid@ri.cmu.edu Abstract
More informationObject. Radiance. Viewpoint v
Fisher Light-Fields for Face Recognition Across Pose and Illumination Ralph Gross, Iain Matthews, and Simon Baker The Robotics Institute, Carnegie Mellon University 5000 Forbes Avenue, Pittsburgh, PA 15213
More informationMulti-view reconstruction for projector camera systems based on bundle adjustment
Multi-view reconstruction for projector camera systems based on bundle adjustment Ryo Furuakwa, Faculty of Information Sciences, Hiroshima City Univ., Japan, ryo-f@hiroshima-cu.ac.jp Kenji Inose, Hiroshi
More information3D Models from Range Sensors. Gianpaolo Palma
3D Models from Range Sensors Gianpaolo Palma Who Gianpaolo Palma Researcher at Visual Computing Laboratory (ISTI-CNR) Expertise: 3D scanning, Mesh Processing, Computer Graphics E-mail: gianpaolo.palma@isti.cnr.it
More informationImage-Based Rendering
Image-Based Rendering COS 526, Fall 2016 Thomas Funkhouser Acknowledgments: Dan Aliaga, Marc Levoy, Szymon Rusinkiewicz What is Image-Based Rendering? Definition 1: the use of photographic imagery to overcome
More informationTEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA
TEXTURE OVERLAY ONTO NON-RIGID SURFACE USING COMMODITY DEPTH CAMERA Tomoki Hayashi, Francois de Sorbier and Hideo Saito Graduate School of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kohoku-ku,
More informationCOMP 102: Computers and Computing
COMP 102: Computers and Computing Lecture 23: Computer Vision Instructor: Kaleem Siddiqi (siddiqi@cim.mcgill.ca) Class web page: www.cim.mcgill.ca/~siddiqi/102.html What is computer vision? Broadly speaking,
More informationMidterm Examination CS 534: Computational Photography
Midterm Examination CS 534: Computational Photography November 3, 2016 NAME: Problem Score Max Score 1 6 2 8 3 9 4 12 5 4 6 13 7 7 8 6 9 9 10 6 11 14 12 6 Total 100 1 of 8 1. [6] (a) [3] What camera setting(s)
More informationcse 252c Fall 2004 Project Report: A Model of Perpendicular Texture for Determining Surface Geometry
cse 252c Fall 2004 Project Report: A Model of Perpendicular Texture for Determining Surface Geometry Steven Scher December 2, 2004 Steven Scher SteveScher@alumni.princeton.edu Abstract Three-dimensional
More informationDirect Methods in Visual Odometry
Direct Methods in Visual Odometry July 24, 2017 Direct Methods in Visual Odometry July 24, 2017 1 / 47 Motivation for using Visual Odometry Wheel odometry is affected by wheel slip More accurate compared
More information3DFaceNet: Real-time Dense Face Reconstruction via Synthesizing Photo-realistic Face Images
1 3DFaceNet: Real-time Dense Face Reconstruction via Synthesizing Photo-realistic Face Images Yudong Guo, Juyong Zhang, Jianfei Cai, Boyi Jiang and Jianmin Zheng arxiv:1708.00980v2 [cs.cv] 11 Sep 2017
More informationCHAPTER 3 DISPARITY AND DEPTH MAP COMPUTATION
CHAPTER 3 DISPARITY AND DEPTH MAP COMPUTATION In this chapter we will discuss the process of disparity computation. It plays an important role in our caricature system because all 3D coordinates of nodes
More informationDA Progress report 2 Multi-view facial expression. classification Nikolas Hesse
DA Progress report 2 Multi-view facial expression classification 16.12.2010 Nikolas Hesse Motivation Facial expressions (FE) play an important role in interpersonal communication FE recognition can help
More informationAccurate 3D Face and Body Modeling from a Single Fixed Kinect
Accurate 3D Face and Body Modeling from a Single Fixed Kinect Ruizhe Wang*, Matthias Hernandez*, Jongmoo Choi, Gérard Medioni Computer Vision Lab, IRIS University of Southern California Abstract In this
More informationFace Morphing using 3D-Aware Appearance Optimization
Face Morphing using 3D-Aware Appearance Optimization Fei Yang 1 Eli Shechtman 2 Jue Wang 2 Lubomir Bourdev 2 Dimitris Metaxas 1 1 Rutgers University 2 Adobe Systems Figure 1: Our system can generate fully
More informationTracking system. Danica Kragic. Object Recognition & Model Based Tracking
Tracking system Object Recognition & Model Based Tracking Motivation Manipulating objects in domestic environments Localization / Navigation Object Recognition Servoing Tracking Grasping Pose estimation
More informationAdvances in Face Recognition Research
The face recognition company Advances in Face Recognition Research Presentation for the 2 nd End User Group Meeting Juergen Richter Cognitec Systems GmbH For legal reasons some pictures shown on the presentation
More informationStructured light 3D reconstruction
Structured light 3D reconstruction Reconstruction pipeline and industrial applications rodola@dsi.unive.it 11/05/2010 3D Reconstruction 3D reconstruction is the process of capturing the shape and appearance
More informationGraphite IntroducDon and Overview. Goals, Architecture, and Performance
Graphite IntroducDon and Overview Goals, Architecture, and Performance 4 The Future of MulDcore #Cores 128 1000 cores? CompuDng has moved aggressively to muldcore 64 32 MIT Raw Intel SSC Up to 72 cores
More informationLast update: May 4, Vision. CMSC 421: Chapter 24. CMSC 421: Chapter 24 1
Last update: May 4, 200 Vision CMSC 42: Chapter 24 CMSC 42: Chapter 24 Outline Perception generally Image formation Early vision 2D D Object recognition CMSC 42: Chapter 24 2 Perception generally Stimulus
More informationUnsupervised Learning
Unsupervised Learning Learning without Class Labels (or correct outputs) Density Estimation Learn P(X) given training data for X Clustering Partition data into clusters Dimensionality Reduction Discover
More information