3D Reconstruction of Human Bodies with Clothes from Un-calibrated Monocular Video Images

Similar documents
Markerless Motion Capture from Single or Multi-Camera Video Sequence

Human Motion Reconstruction and Animation from Video Sequences

Human Body Shape Deformation from. Front and Side Images

Automatic Generation of Animatable 3D Personalized Model Based on Multi-view Images

Clothed and Naked Human Shapes Estimation from a Single Image

Statistical Learning of Human Body through Feature Wireframe

THREE-dimensional models of human body are widely

International Conference on Communication, Media, Technology and Design. ICCMTD May 2012 Istanbul - Turkey

Capturing Skeleton-based Animation Data from a Video

Single-View Dressed Human Modeling via Morphable Template

Automatic Modeling of Virtual Humans and Body Clothing

Estimation of Human Body Shape in Motion with Wide Clothing

Personalization and Evaluation of a Real-time Depth-based Full Body Tracker

arxiv: v2 [cs.cv] 3 Mar 2017

Topics in Computer Animation

Estimating 3D Human Shapes from Measurements

3D Modeling of Humans with Skeletons from Uncalibrated Wide Baseline Views

SCAPE: Shape Completion and Animation of People

Research Article Human Model Adaptation for Multiview Markerless Motion Capture

Human hand adaptation using sweeps: generating animatable hand models ...

Motion Graphs for Character Animation

Rapid Skin: Estimating the 3D Human Pose and Shape in Real-Time

Shape Customisation of Human Subjects Based on Human Parsing Technology

Parametric Editing of Clothed 3D Avatars

To Do. Advanced Computer Graphics. The Story So Far. Course Outline. Rendering (Creating, shading images from geometry, lighting, materials)

Course Outline. Advanced Computer Graphics. Animation. The Story So Far. Animation. To Do

Comparison of Default Patient Surface Model Estimation Methods

A Data-Driven Approach for 3D Human Body Pose Reconstruction from a Kinect Sensor

A Validation Study of a Kinect Based Body Imaging (KBI) Device System Based on ISO 20685:2010

To Do. History of Computer Animation. These Lectures. 2D and 3D Animation. Computer Animation. Foundations of Computer Graphics (Spring 2010)

Animations. Hakan Bilen University of Edinburgh. Computer Graphics Fall Some slides are courtesy of Steve Marschner and Kavita Bala

Markerless Motion Capture with Multi-view Structured Light

Calibrated Image Acquisition for Multi-view 3D Reconstruction

CSE452 Computer Graphics

Dynamic Human Shape Description and Characterization

Motion Synthesis and Editing. Yisheng Chen

A Model-based Approach to Rapid Estimation of Body Shape and Postures Using Low-Cost Depth Cameras

Graphics, Vision, HCI. K.P. Chan Wenping Wang Li-Yi Wei Kenneth Wong Yizhou Yu

Data-driven Depth Inference from a Single Still Image

Computer Vision at Cambridge: Reconstruction,Registration and Recognition

Making Machines See. Roberto Cipolla Department of Engineering. Research team

Keyframe Animation. Computer Animation. Outline. Computer Animation. Keyframe Animation. Keyframe Animation

3D Human Motion Analysis and Manifolds

A Multiresolutional Approach for Facial Motion Retargetting Using Subdivision Wavelets

Thiruvarangan Ramaraj CS525 Graphics & Scientific Visualization Spring 2007, Presentation I, February 28 th 2007, 14:10 15:00. Topic (Research Paper):

Monocular Tracking and Reconstruction in Non-Rigid Environments

International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XXXIV-5/W10

Deformation Transfer for Triangle Meshes

Probabilistic Tracking and Reconstruction of 3D Human Motion in Monocular Video Sequences

Kinematics & Motion Capture

EPFL. When an animator species an animation sequence, it privileges when animating the Virtual. body, the privileged information to be manipulated

Future Studios Research Lab

Reverse Engineering Garments

From 3-D Scans to Design Tools

Clothes Size Prediction from Dressed-human Silhouettes

Animating Characters in Pictures

A Novel Illumination-Invariant Loss for Monocular 3D Pose Estimation

A Data-driven Approach to Human-body Cloning Using a Segmented Body Database

AN ONTOLOGY OF VIRTUAL HUMANS: INCORPORATING SEMANTICS INTO HUMAN SHAPES

Computer Animation Visualization. Lecture 5. Facial animation

The 3D rendering pipeline (our version for this class)

Motion Capture Using Joint Skeleton Tracking and Surface Estimation

Statistics and Information Technology

Human Upper Body Pose Estimation in Static Images

arxiv: v1 [cs.cv] 28 Jul 2016

Automatic Animation of High Resolution Images

Im2Fit: Fast 3D Model Fitting and Anthropometrics using Single Consumer Depth Camera and Synthetic Data

Creating Custom Human Avatars for Ergonomic Analysis using Depth Cameras

Motion Capture, Motion Edition

Space-time Body Pose Estimation in Uncontrolled Environments

3D Production Pipeline

Animation of Refitted 3D Garment Models for Reshaped Bodies

A Pose Invariant Statistical Shape Model for Human Bodies

3D Modeling for Capturing Human Motion from Monocular Video

Continuous and Discrete Optimization Methods in Computer Vision. Daniel Cremers Department of Computer Science University of Bonn

COMP 175 COMPUTER GRAPHICS. Lecture 10: Animation. COMP 175: Computer Graphics March 12, Erik Anderson 08 Animation

CS 231. Motion Capture Data I. The Pipeline. Bodenheimer et al

An Investigation on the Framework of Dressing Virtual Humans

Motion Control with Strokes

3D reconstruction of static human body with a digital camera

Semi-Automatic Prediction of Landmarks on Human Models in Varying Poses

ASIAGRAPH 2008 The Intermediate View Synthesis System For Soccer Broadcasts

3D model-based human face modeling

Body Scanning and Modeling for Custom Fit Garments. B. Xu, Y. Huang, W. Yu and T. Chen

Computer Vision : Exercise 4 Labelling Problems

Registration of Deformable Objects

Animation. CS 465 Lecture 22

Deep Learning for Virtual Shopping. Dr. Jürgen Sturm Group Leader RGB-D

Measurement of 3D Foot Shape Deformation in Motion

05 Mesh Animation. Steve Marschner CS5625 Spring 2016

Computer Vision and Virtual Reality. Introduction

Motion Capture using Body Mounted Cameras in an Unknown Environment

Free-Form Mesh Tracking: a Patch-Based Approach

CS-184: Computer Graphics

arxiv: v2 [cs.cv] 19 Nov 2014

M I RA Lab. Speech Animation. Where do we stand today? Speech Animation : Hierarchy. What are the technologies?

Dynamic Shape Tracking via Region Matching

Modeling of Bodies and Clothes for Virtual Environments

Virtual Try-0N System

animation projects in digital art animation 2009 fabio pellacini 1

Transcription:

3D Reconstruction of Human Bodies with Clothes from Un-calibrated Monocular Video Images presented by Tran Cong Thien Qui PhD Candidate School of Computer Engineering & Institute for Media Innovation Supervisor: Co-Supervisor: Prof. Seah Hock Soon Prof. Nadia Magnenat Thalmann 9 November 2010

Outline Motivation Research Objectives Literature Review Proposed Research Method Current Work Further Work

Motivation Ability to clone human body is necessary for many different applications Animation & movies Avatars for games Crowd simulation Medical applications Sport Analysis Fashion (Beowulf 2007) (Crowd Simulation -VRlab, EPFL)

Motivation Traditional Laser Scanners Incomplete surface data Tedious, manual process Do not have skeleton information Expensive Multi-camera setup (Cyberware Scanner) Difficult to setup Calibrate and synchronize Lighting condition Limit its applications (D. Vlasic et. al. Siggraph Asia 09)

Research Objectives 3D Reconstruction of Human Bodies with Clothes from Un-calibrated Monocular Video Images Video Images from A Single Camera 3D Geometry of human body (Animatable) 3D Geometry of Clothes

Literature Review Human Body Reconstruction Has been an open research for a long time Can be categorized into 3 groups Approaches with no body template Shape-from-silhouette Approaches with a human model template Sample-based approaches

Literature Review Reconstruction with a human model template VRML H-Anim 1.1 [W. Lee, J. Gu and N.M. Thalmann 2000] VRML model [Hilton 2000] Soft models using metaball representation [Fua 2003] Generic template [D. Grest 2005] Generic template with B-spline curves [Theobalt 2005] ( J. Shen and D. Thalmann 1995) ( D. Grest 2005) (W. Lee, J. Gu and N.M. Thalmann 2000 )

Literature Review Sample-based Reconstruction Using many 3D body scans to learn the space of human body shape [H. Seo and N.M. Thalmann 2003] (57 females subjects in one posture) [Allen and Popovic 2003] (250 male and female subjects in one posture) [Anguelov 2005] (37 subjects in A pose + 1 subject in 70 postures) [Hasler 2009] (114 male and female subjects in 34 postures)

Literature Review 3D Reconstruction of human body from a single camera P. Guan, A. Weiss, A. O. Bălan, M. J. Black, Estimating Human Shape and Pose from a Single Image, ICCV 2009 Limited to naked-like subjects Only applied to one single image N. Hasler, H. Ackermann, B. Rosenhahn, T. Thormaḧlen, H. P. Seidel,: Multilinear pose and body shape estimation of dressed subjects from image sets, CVPR 2010 Manual input is needed for each image to detect posture Only uses image silhouette Loose clothes have not been fully addressed (Guan - ICCV 09) (Hasler- CVPR 10)

Literature Review 3D Reconstruction of human body from a single camera N. Hasler, H. Ackermann, B. Rosenhahn, T. Thormaḧlen, H. P. Seidel,: Multilinear pose and body shape estimation of dressed subjects from image sets, CVPR 2010 Loose clothes have not been fully addressed

Proposed Research Method Using video as input Increase the accuracy Help in separating human body and clothes Cloth deformation by motion can be used to verify the body geometry How to determine postures for each image frame? User will annotate some markers on keyframe images In-between posture will be interpolated

Proposed Research Method Manual Input in key frames Body Database Video Image s Keyframe Annotation Postures Fitting Body Model Estimated Body Geometry Silhouette Segmentation Silhouette Body Geometry Extract Garments Garment Database Bundle adjustment across the video sequence Cloth Geometry Body Geometry Cloth Geometry

Proposed Research Method Bundle Adjustment to adjust all the parameters Parameters: Postures, Body Sizes, Cloth Sizes Silhouette Error Function: the differences between silhouettes and the projection images of the model ( pos, bodysizes, clothsizes) Arg min ( f ( pos, bodysizes, clothsizes) sil ) pos : 3D positions, joint angles in frame i i i i i i bodysizes: sizing parameters of human body clothsizes: sizing parameters of clothes sil : silhouettes extracted from frame i i 2

Current Work Silhouette Segmentation C. Rother, V. Kolmogorov, A. Blake. - SIGGRAPH 04 GrabCut: Interactive Foreground Extraction using Iterated Graph Cuts.

Further Work Keyframe annotation and interpolation Resizing human model to fit the extracted silhouette Extracting garments

Thank you!