Skull Assembly and Completion using Template-based Surface Matching

Similar documents
An Automatic Assembly and Completion Framework for Fragmented Skulls

An Interactive System for Heterogeneous 3D Volumetric Data Visualization

Correspondence. CS 468 Geometry Processing Algorithms. Maks Ovsjanikov

Accurate Reconstruction by Interpolation

Geometric Registration for Deformable Shapes 3.3 Advanced Global Matching

Preparation Meeting. Recent Advances in the Analysis of 3D Shapes. Emanuele Rodolà Matthias Vestner Thomas Windheuser Daniel Cremers

Recognizing Deformable Shapes. Salvador Ruiz Correa UW Ph.D. Graduate Researcher at Children s Hospital

Design Intent of Geometric Models

Non-Experts Shape Modeling for Dummies

Advances in Forensic Anthropology

Translation Symmetry Detection: A Repetitive Pattern Analysis Approach

Recognizing Deformable Shapes. Salvador Ruiz Correa Ph.D. Thesis, Electrical Engineering

Recognizing Deformable Shapes. Salvador Ruiz Correa (CSE/EE576 Computer Vision I)

Lecture 8 Object Descriptors

Deformable Registration of Cortical Structures via Hybrid Volumetric and Surface Warping

3D model-based human face modeling

3D Object Scanning to Support Computer-Aided Conceptual Design

Properties of Quadratic functions

Recognizing Deformable Shapes. Salvador Ruiz Correa Ph.D. UW EE

EFFICIENT 3D REGION GUARDING FOR MULTIMEDIA DATA PROCESSING

Registration of Dynamic Range Images

Monocular Template-based Reconstruction of Inextensible Surfaces

FAST REGISTRATION OF TERRESTRIAL LIDAR POINT CLOUD AND SEQUENCE IMAGES

Design Intent of Geometric Models

Warping and Morphing. Ligang Liu Graphics&Geometric Computing Lab USTC

Use of Shape Deformation to Seamlessly Stitch Historical Document Images

Reconstruction of complete 3D object model from multi-view range images.

Subdivision Curves and Surfaces

Robotics Programming Laboratory

Mathematical Tools for 3D Shape Analysis and Description

CREATING 3D WRL OBJECT BY USING 2D DATA

3D Modeling using multiple images Exam January 2008

Subdivision Surfaces. Homework 1: Last Time? Today. Bilinear Patch. Tensor Product. Spline Surfaces / Patches

The correspondence problem. A classic problem. A classic problem. Deformation-Drive Shape Correspondence. Fundamental to geometry processing

Dynamic Geometry Processing

Laplacian Meshes. COS 526 Fall 2016 Slides from Olga Sorkine and Yaron Lipman

Detecting Multiple Symmetries with Extended SIFT

Registration of Deformable Objects

Accurate 3D Face and Body Modeling from a Single Fixed Kinect

Exploring Collections of 3D Models using Fuzzy Correspondences

Finding Surface Correspondences With Shape Analysis

Structured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov

Meshless Modeling, Animating, and Simulating Point-Based Geometry

Easy modeling generate new shapes by deforming existing ones

Human-body modeling Xi et al. [3] used non-numerical attributes like gender, age, race, marital status, and occupation to predict body shapes and buil

Non-rigid Image Registration using Electric Current Flow

MPEG-7 Visual shape descriptors

Occluded Facial Expression Tracking

Global Shape Matching

Exact Volume of Hyperbolic 2-bridge Links

L1 - Introduction. Contents. Introduction of CAD/CAM system Components of CAD/CAM systems Basic concepts of graphics programming

Bayesian Spherical Wavelet Shrinkage: Applications to Shape Analysis

Discovering Similarities in 3D Data

CSE 554 Lecture 7: Deformation II

Deformation Transfer for Triangle Meshes

04 - Normal Estimation, Curves

Scanning Real World Objects without Worries 3D Reconstruction

Integrated High-Quality Acquisition of Geometry and Appearance for Cultural Heritage

Template For Rectangular Based Pyramid

Geometry based Repetition Detection for Urban Scene

1. Introduction. 2. Parametrization of General CCSSs. 3. One-Piece through Interpolation. 4. One-Piece through Boolean Operations

Students are not expected to work formally with properties of dilations until high school.

3D Object Representation. Michael Kazhdan ( /657)

Mesh Processing Pipeline

Yaron Lipman Thomas Funkhouser. RifR Raif Rustamov. Princeton University. Drew University

Improving Image Segmentation Quality Via Graph Theory

IMAGE-BASED RENDERING

Non-rigid Image Registration

Subdivision Surfaces. Course Syllabus. Course Syllabus. Modeling. Equivalence of Representations. 3D Object Representations

A Hierarchical Compositional System for Rapid Object Detection

ACQUIRING 3D models of deforming objects in real-life is

Parametric Modeling Design and Modeling 2011 Project Lead The Way, Inc.

DIGITAL DESIGN STRATEGIES

Snakes, level sets and graphcuts. (Deformable models)

Compu&ng Correspondences in Geometric Datasets. 4.2 Symmetry & Symmetriza/on

MA 323 Geometric Modelling Course Notes: Day 21 Three Dimensional Bezier Curves, Projections and Rational Bezier Curves

Topology-Invariant Similarity and Diffusion Geometry

Dgp _ lecture 2. Curves

Improving Shape retrieval by Spectral Matching and Meta Similarity

Shape Constancy and Shape Recovery: wherein Human and Computer Vision Meet

Integrated Projects. Madonna di Pietranico Pompeii insula V1 V I S UA L COMPUTING L A B I ST I - C N R

Separating Objects and Clutter in Indoor Scenes

Semi-Supervised Hierarchical Models for 3D Human Pose Reconstruction

Real-Time Shape Editing using Radial Basis Functions

Using Geometric Blur for Point Correspondence

Geometric-Feature-Based Spectral Graph Matching in Pharyngeal Surface Registration

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Spatio-Temporal Fusion of Multiple View Video Rate 3D Surfaces

Shape Matching and Object Recognition using Low Distortion Correspondences

NESTED AND FULLY AUGMENTED LINKS

1 Introduction Motivation and Aims Functional Imaging Computational Neuroanatomy... 12

3D Digitization of Human Foot Based on Computer Stereo Vision Combined with KINECT Sensor Hai-Qing YANG a,*, Li HE b, Geng-Xin GUO c and Yong-Jun XU d

Shape analysis through geometric distributions

Geometric Registration for Deformable Shapes 1.1 Introduction

Face Alignment Under Various Poses and Expressions

Data Representation in Visualisation

Seeing the unseen. Data-driven 3D Understanding from Single Images. Hao Su

Active Contour and Seismic Interpretation

Surface Modeling. Polygon Tables. Types: Generating models: Polygon Surfaces. Polygon surfaces Curved surfaces Volumes. Interactive Procedural

Surgery Simulation and Planning

Transcription:

Skull Assembly and Completion using Template-based Surface Matching Li Wei, Wei Yu, Maoqing Li 1 Xin Li* 2 1 School of Information Science and Technology Xiamen University 2 Department of Electrical and Computer Engineering Center for Computation and Technology Louisiana State University *EMail: xinli@lsu.edu 3DIMPVT 2011 1 / 17

Introduction Goal To assemble and repair fragmented skulls to complete models. Motivation Skull Completion is important in forensic and anthropological facial reconstruction. The traditional state-of-the-art approach: Time consuming Domain expertise required Subjective when large regions are missing Proposed Approach: Computer-aided completion in digital environment 2 / 17

Introduction Assembling Completion Results Conclusion Related Work 3 / 17

Algorithm Pipeline 4 / 17

Fragmented Skull Assembling In: A set of fragments M i and template S. Out: A set of rigid transformations T i (applied on M i ), so that the arrangement of all fragments in world coordinates well approximates S. 5 / 17

Feature Exaction Feature Extraction Slippage Feature on each Fragment M i. Signature Spin Image [Johnson et al. 1999]. Why Spin Image? Comparing the Geometric Properties of regions. Our Modified Spin-Image Signature Resolution-Invariance Direction Filtering 6 / 17

Finding Coarse Correspondence I/O In: Spin image signatures on fragments feature points and template points. Out: Correspondence from feature points (on fragments) to the template. The most possible many-to-many mapping (most similar corresponding pairs of points) is the coarse correspondence. 7 / 17

Fragment-Template Matching Optimal Correspondence Exact a most isometric sub-set [Tevs et al. 2009]. Local Registration Compute rigid transform by optimal corresponding. 8 / 17

Inter-Fragment Refinement Avoid Intersection Between Fragments Refinement: Taking the computed transformations as starting variables, to minimize the objective function composed of three terms: E(T 1,..., T n) = αe I + βe F + γe T, where E I = i,j n,i<j Int(T i(m i ), T j (M j )), E F = i v T i (M i ) Dis(v, S) 2, E T = i S(T i). 9 / 17

Skull Completion I/O In: The assembled skull with damage regions, and a template. Out: A repaired skull The completion is based on the surface matching between the the template and subject skull. 10 / 17

Template-based Completion Non-rigid Template/Subject Mapping In: A template model, and the assembled skull. Out: Affine transformations on each template vertex Minimizing the following matching energy: E = λ 1 E data + λ 2 E shape where E data = Dis 2 (T i + v i, M) v i S E shape = T i T j 2 e i,j,v i,v j S 11 / 17

Template-based Completion I/O In: Deformed template and assembled object skull. Out: Repaired object skull Cut and paste. Filling small holes/gaps[liepa et al. 2003] Smoothing[Kobbelt et al. 1998] 12 / 17

Experimental Results 13 / 17

Completion in Various Cases 14 / 17

Conclusion Skull Assembling: Fragment-template matching > Spatial relationship of fragments. Robust and efficient partial matching by improved spin image. Global refinement to reduce self intersection. Skull Completion: Non-rigid registration from template to object. Robust hole-filling and smoothing algorithm. 15 / 17

Acknowledgements The Skull Data are provided by the Forensic Anthropology and Computer Enhancement Services (FACES) Laboratory at Louisiana State University This work is supported by Louisiana Board of Regents Research Competitiveness Subprogram (RCS) LEQSF(2009-12)-RD-A-06, PFund: NSF(2009)-PFund-133, and LSU Faculty Research Grant 2010. Project Website: http://www.ece.lsu.edu/xinli/skullassembly.html 16 / 17

On-going and Future Work Assembly Increase accuracy by analyzing break curves. Completion Intergrate the completion using symmetry. Facial reconstruction Digital face modeling on completed skull 17 / 17