Welcome to the 2009 IEEE International Workshop on 3-D Digital Imaging and Modeling. Organized every two years  since 1997, 3DIM is the principal forum for researchers interested in all aspects of optical acquisition and computational analysis and transformation of 3D information. Held this year as a ICCV two-day workshop, 3DIM 2009 received a large number of submissions (129), which imposed difficult choices in the paper selection. Each submission was sent for review to three members of the Program Committee or additional reviewers. Based on these evaluations and assessment by the Chairs, papers with the highest degrees of new contributions and clarity of exposition were selected: 18 papers were chosen for oral presentations, while 41 were selected for poster presentations (one paper was withdrawn after acceptance). We are pleased to present a program of high quality papers covering all aspects of 3D imaging and modeling, that will be of interest not only to the core 3DIM audience but also to the wider computer vision research community attending ICCV. The program also includes invited talks by three leading researchers in the field, Edmond Boyer, Brian Curless and Ron Kimmel.

We wish to thank all those who submitted papers to 3DIM 2009. We thank the members of the program committee as well as the additional reviewers for their essential role in making the workshop a success. We also thank for their support the ICCV 2009 Workshop Chairs Yoichi Sato and Yoav Schechner, the ICCV 2009 Publication Chair Hirokazu Kato, and all the ICCV 2009 Organizers.

Welcome to 3DIM 2009.

Learning Shape Priors for Single View Reconstruction
Yu Chen, Roberto Cipolla   

Training Many-parameter Shape-from-shading Models Using a Surface Database   
Nazar Khan, Lam Tran, Marshall Tappen

Isometry, Symmetry and Biometry: The Gromov-Hausdorff Distance in Action

The Gromov-Hausdorff distance or d_GH is a definition for the discrepancy between metric spaces. Until recently, it has been applied mainly in theoretical research of metric spaces in metric geometry, as well as in theoretical computer science, specifically, in the context of metric embedding. In this talk we will explore the relation between d_GH and multi-dimensional scaling (MDS), a classical approach for embedding a given metric space into one in which distances can be analytically computed. The obvious example for such a target embedding space is Euclidean. Specifically, we use the Generalized MDS (GMDS) as a building block in approximating d_GH. The exposition of ideas in metric geometry and numerical optimization will be motivated through practical examples like 3D face recognition, texture mapping in computer graphics, and more.

Ron Kimmel is Professor of Computer Science at the Technion, Israel Institute of Technology. He held a post-doctoral position at UC Berkeley and a visiting professorship at Stanford University. He has worked in various areas of computer vision, image processing, and computer graphics. Kimmel's interest in recent years has been non-rigid shapes, medical imaging and computational biometry, numerical optimization, and applications of metric and differential geometry. Kimmel is an IEEE Fellow for his contributions to image processing and non-rigid shape analysis. He is an author of two books and numerous articles. He is the founder of the Geometric Image Processing Lab. and a founder and advisor of several successful companies.

LiDAR Inpainting from a Single Image
Jacob Becker, Charles Stewart, Richard J. Radke

A High Speed Iterative Closest Point Tracker on an FPGA Platform
Michael S. Belshaw, Michael A. Greenspan    
 
Fully Automatic Calibration of LIDAR and Video Streams from a Vehicle
Stanley Bileschi    

Iterative Mesh Deformation for Dense Surface Tracking
Cedric Cagniart, Edmond Boyer, Slobodan Ilic  

Measuring 3D Shape Similarity by Matching the Medial Scaffolds
Ming-Ching Chang, Benjamin B. Kimia   

Consistency and Confidence: A Dual Metric for Verifying 3D Object Detections in Multiple LiDAR Scans
David L. Doria, Richard J. Radke    
  
Structure-and-motion Pipeline on a Hierarchical Cluster Tree
Michela Farenzena, Andrea Fusiello, Riccardo Gherardi    
   
Automatic Bootstrapping of a Morphable Face Model using Multiple Components
Frank B. ter Haar, Remco C. Veltkamp    
   
3D-Color Video Camera
O. Rubinstein, Y. Honen, A. M. Bronstein, M. M. Bronstein, R. Kimmel    
 
Shape-Colour Histograms for Matching 3D Video Sequences
Peng Huang, Adrian Hilton    
 
Real-time Photo-realistic Visualization of 3D Environments for Enhanced Tele-operation of Vehicles
Daniel Huber, Herman Herman, Alonzo Kelly, Peter Rander, Jason Ziglar    
 
Scalable Multi-view Stereo
Michal Jancosek, Alexander Shekhovtsov, Tomas Pajdla    
 
Environment Modelling Using Spherical Stereo Imaging
Hansung Kim, Adrian Hilton    

Multi-view Image and ToF Sensor Fusion for Dense 3D Reconstruction
Young Min Kim, Christian Theobalt, James Diebel, Jana Kosecka, Branislav Micusik, Sebastian Thrun    
 
Shape from Depth Discontinuities under Orthographic Projection
Douglas Lanman, Daniel Cabrini Hauagge, Gabriel Taubin   
  
Elastic Convolved ICP for the Registration of Deformable Objects
Ryusuke Sagawa, Kiyotaka Akasaka, Yasushi Yagi, Henning Hamer, Luc Van Gool    
  
Color Matching and Illumination Estimation for Urban Scenes
Mingxuan Sun, Grant Schindler, Greg Turk, Frank Dellaert    
   
Posture Invariant Correspondence of Triangular Meshes in Shape Space
Stefanie Wuhrer, Chang Shu, Prosenjit Bose    
 
A Minimum Cover Approach for Extracting the Road Network from Airborne LIDAR Data
Qihui Zhu, Philippos Mordohai    
 
Freeform Shape Clustering for Customized Design Automation
Alexander Zouhar, Sajjad Baloch, Sergei Azernikov, Claus Bahlmann, Gozde Unal, Tong Fang, Siegfried Fuchs    

Hierarchical Shape-based Surface Reconstruction for Dense Multi-view Stereo
Patrick Labatut, Jean-Philippe Pons, Renaud Keriven    

Self-Correction of 3D Reconstruction from Multi-view Stereo Images
Xiangyang Ju, J Paul Siebert, Balvinder S Khambay, Ashraf F Ayoub    

Robust Multi-View Stereo without Matching
Philippe Lambert, Patrick Hébert    
 
Plenoptic Depth Estimation From Multiple Aliased Views
Tom E. Bishop, Paolo Favaro   

Modeling Dynamic Scenes using Meshes

Recovering dynamic shapes from videos is a challenging topic in computer vision and computer graphics  with many important applications in 3D modeling, scene analysis  and animation among others. In this talk, I will present activities conducted at the INRIA Grenoble in this field over the last years.  In particular, I will discuss the use of meshes to model photometric shapes that evolve over time.  Meshes have recently gained popularity to represent  and  track shape deformations using multiple videos. I will present tools that  we have developed for this  purpose as well as the results obtained on challenging temporal sequences.  I will also discuss issues and prospects  in this domain.

Edmond Boyer received the MS degree in signal processing  in 1993 and the PhD degree in computer science from the Institut  National Polytechnique de Lorraine-Nancy (France) in 1996. He was a post-doctoral visitor at the University of Cambridge (UK) in 1998. He is currently an associate Professor of computer science at the University Joseph Fourier, Grenoble (France), and a researcher at the INRIA Grenoble since 1998 (http://perception.inrialpes.fr/).  He has published widely in computer vision, computational geometry and virtual reality.  He  is also co-founder of the 4D View Solution Company (http://www.4dviews.com/). His current research interests are on 3D dynamic modeling from images and videos, motion capture, action recognition from videos, and multiple camera environments.

In-Hand Scanning with Online Loop Closure
Thibaut Weise, Thomas Wismer, Bastian Leibe, Luc Van Gool

Online Segmentation of Free-viewpoint Video
Masato Ishii, Keita Takahashi, Takeshi Naemura    

Spatio-temporal Image-based Texture Atlases for Dynamic 3-D Models
Zsolt Janko, Jean-Philippe Pons    

Robust Range Image Registration Using Local Distribution of Albedo   
Diego Thomas, Akihiro Sugimoto    
 
Complex 3D Shape Recovery using Hybrid Geometric Shape Features in a Hierarchical Shape Segmentation Approach    
Hongwei Zheng, Dietmar Saupe   

Multi-view Stereo: Out of the Petri Dish and into the Wild

Reconstructing scenes from photographs -- multi-view stereo -- is experiencing a new renaissance.  Once a tool for creating fairly crude models in laboratory settings, it has grown into a powerful ally for
high quality image-based modeling and rendering of real-world scenes. In this talk, I will describe our recent progress on and new applications of multi-view stereo.  Our algorithms are designed to work on a variety of inputs, including videos, personal photos, and internet photo collections.  I will show how these algorithms can be adapted for visual effects, enhancing and experiencing personal photos, and reconstructing shape in difficult architectural settings. Finally, I will conclude with thoughts on the future of this field.

Brian Curless is an Associate Professor of Computer Science & Engineering at the University of Washington.  He is a member of the Graphics and Imaging Laboratory (GRAIL), a group dedicated to innovation in computer graphics and vision.  He received a PhD in Electrical Engineering at Stanford University, where he helped co-found the Digital Michelangelo Project.  He received the Gores Teaching Award and the Arthur Samuels Computer Science Thesis Award while at Stanford, and an NSF Career Award, Sloan Fellowship, and ACM Student Chapter Teaching Award while at the University of Washington. He is also co-founder and co-editor-in-chief of the journal Foundations and Trends in Computer Graphics and Vision.  His research is currently focused on computational and 3D photography.

Fast 3D Surface Reconstruction by Unambiguous Compound Phase Coding
Andrea Albarelli, Emanuele Rodolà, Samuel Rota Bulò, Andrea Torsello

A Probabilistic Approach to Camera Pose and Calibration from a Small Set of Point and Line Correspondences
Thomas Chaperon, Jacques Droulez, Guillaume Thibault   
   
Tackling the Coplanarity Problem in 3D Camera Calibration by Means of Fuzzy Landmarks: a Performance Study in Forensic Craniofacial Superimposition
J. Santamaria, O. Cordon, S. Damas, O. Ibañez
  
Context-Consistent Stereo Matching
Shufei Fan, Frank Ferrie    
  
Monocular Structure from Motion for Near to Long Ranges
John Fields, Garbis Salgian, Supun Samarasekera, Rakesh Kumar    
  
Automation of 3D View Acquisition for Geometric Tolerances Verification
Michele Germani,  Maura Mengoni, Roberto Raffaeli
   
Creating Compact Architectural Models by Geo-registering  Image Collections
Radek Grzeszczuk, Jana Kosecka, Ramakrishna Vedantham, Harlan Hile

Local Potential Well Space Embedding
Yani Ioannou, Limin Shang, Robin Harrap, Michael Greenspan

On-line 3-D Inspection of Deformable Parts  Using  FEM Trained  Radial Basis Functions
Andrés E. Jaramillo, Pierre Boulanger, Flavio Prieto    
   
Real-Time Free Viewpoint Video from Uncalibrated Cameras Using Plane-sweep Algorithm
Songkran Jarusirisawad, Hideo Saito,  Vincent Nozick
   
Improving Photometric Stereo with Laser Sectioning
Junyu Dong, G. McGunnigle, Liyuan Su, Yanxia Fang, Yuliang Wang

Mobile Phone-based 3D Modeling Framework for Instant Interaction
Wonwoo Lee, Kiyoung Kim, Woontack Woo    
   
A Locally Global Approach to Stereo Correspondence
Stefano Mattoccia   

 An Efficient Data-driven Tissue Deformation Model
Thomas Hammershaimb Mosbech, Bjarne Kjar Ersboll, Lars Bager Christensen
   
Markerless Reconstruction of Dynamic Facial Expressions
Dominik Sibbing, Martin Habbecke, Leif Kobbelt    
 
One-Shot Scanning using De Bruijn Spaced Grids
Ali Osman Ulusoy, Fatih Calakli, Gabriel Taubin
  
A Compact Representation for Scanned 3D Objects
Bing Wang, Holly Rushmeier    
   
Region Extraction in Large-Scale Urban LIDAR Data
Alexandri Zavodny, Patrick Flynn, Xin Chen    
   
Virtual 3D Bone Fracture Reconstruction via Inter-fragmentary Surface Alignment
Beibei Zhou, Andrew Willis, Yunfeng Su, Donald D. Anderson, Thomas D. Brown, Thaddeus Thomas
   
Optimal Consensus Set for Digital Plane Fitting
Rita Zrour, Yukiko Kenmochi, Hugues Talbot, Lilian Buzer, Yskandar Hamam, Ikuko Shimizu, Akihiro Sugimoto    

Tracking Human Joint Motion for Turntable-based Static Model Reconstruction
Neil Birkbeck, Dana Cobzas, Martin Jagersand    
   
Shade Face: Multiple Image-Based 3D Face Recognition
Ajmal S. Mian    
 
Robust 3D Street-view Reconstruction Using Sky Motion Estimation
Taehee Lee 
 
Large-scale Urban Environment Modeling from Videos Using Image Content Segmentation and Alignment
Xiang Zhang, Jonathan T. Blocksom, Dale D. Miller   

Sampled Medial Loci and Boundary Differential Geometry
Svetlana Stolpner, Sue Whitesides, Kaleem Siddiqi    
  
Fast Computation of 3D Spherical Fourier Harmonic Descriptors -  A Complete Orthonormal Basis for a Rotational Invariant Representation of  Three-Dimensional Objects
Henrik Skibbe, Marco Reisert, Qing Wang, Olaf Ronneberger, Hans Burkhardt    

Disparity Map Refinement and 3D Surface Smoothing via Directed Anisotropic Diffusion
Atsuhiko Banno, Katsushi Ikeuchi    

____________________________________