3DIMPVT
     
 
Monday Start Tuesday Start Wednesday Start Thursday Start
Tutorial 1: 9:00 Opening 9:00 Announcements 9:00 Announcements 9:00

Structured Light Systems

By: Hiroshi Kawasaki &
Ryusuke Sagawa

LUNCH INCLUDED

  Invited Talk 1 9:15 Invited talk 2 9:00 Session 3A 9:00
  Break 10:15 Break 10:00 Break 10:30
Session 1A 10:45 Session 2A 10:30 Session 3B 11:00
12:00 Lunch 12:05 Lunch 12:00 Lunch 12:05
Tutorial 2: 13:30 Session 1B 13:30 Session 2B 13:30 Session 3C 13:30

Geometric Modeling and Processing,

By: Ligang Liu

  Break 14:50 Break 14:50 Break 14:50
  Session 1C 15:15 Session 2C 15:15 Posters 15:15
  Poster (regular and short paper) 16:35 Poster and Demos 16:35 Invited Talk 3 16:45
Reception 16:30 Dinner & Performance 18:00 Banquet 18:00   18:00
 

 

 


MONDAY:

Tutorial 1:  9:00 to 12:00

Recent Active 3D Scanning System and Techniques
By: Hiroshi Kawasaki & Ryusuke Sagawa
Link to paper

 

Tutorial 2:  13:30 to 16:30

Geometric Modeling and Processing
By: Ligang Liu
Link to presentation 1
Link to presentation 2
Link to presentation 3
Link to presentation 4
Link to presentation 5

 

 

TUESDAY:

Invited talk 1

Kari Pulli
NVIDIA Research

Title: FCam -- An architecture and API for computational cameras

Abstract: FCam (short for Frankencamera) is an architecture for computational cameras and an API that implements the architecture. Our motivation is flexible programming of cameras, especially camera phones. This talk gives an overview of the API and discusses two implementations, one on N900, a
Linux-bases smart phone from Nokia, and "F2", a research camera built at Stanford University that allows experimentation with different sensors and optics. We also describe several applications developed on top of FCam, and FCam use at universities in research and teaching, so far in North America, South America, Europe, and Asia.

Link to presentation

 

 

TUESDAY:

Session 1A


Cutting-Plane Training of Non-associative Markov Network for 3D Point Cloud Segmentation
Roman Shapovalov and Alexander Velizhev
Link to presentation

Toward Automatic 3D Generic Object Modeling from One Single Image
Min Sun, Shyam Sunder Kumar, Gary Bradski, and Silvio Savarese
Link to presentation

Dynamic Shape Capture via Periodical-illumination Optical Flow Estimation and Multi-view Photometric Stereo
Ying Fu, Yebin Liu, and Qionghai Dai
Link to presentation

Surface Reconstruction in Photometric Stereo with Calibration Error
Michihiro Kobayashi, Takahiro Okabe, Yasuyuki Matsushita, and Yoichi Sato
Link to presentation

3D Reconstruction of Urban Areas
Charalambos Poullis and Suya You
Link to presentation

Pseudo-Immersive Realtime Display of 3D Scenes on Mobile Devices
Ming Li, Arne Schmitz, and Leif Kobbelt
Link to presentation

 

 

TUESDAY:

Session 1B


A System for Capturing Textured 3D Shapes based on One-shot Grid Pattern with Multi-band Camera and Infrared Projector
Kazuhiro Sakashita, Yasushi Yagi, Ryusuke Sagawa, Ryo Furukawa, and Hiroshi Kawasaki

Scene Segmentation Assisted by Stereo Vision
Carlo Dal Mutto, Pietro Zanuttigh, Guido M. Cortelazzo, and Stefano Mattoccia

Scalable Object Classification using Range Images
Eunyoung Kim and Gerard Medioni
Link to presentation

Real-Time Accurate Stereo using Modified Two-Pass Aggregation and Winner-Take-All Guided Dynamic Programming
Xuefeng Chang, Zhong Zhou, Liang Wang, Yingjie Shi, and Qinping Zhao
Link to presentation

Robust ICP Registration using Biunique Correspondence
Lei Zhang, Sung-In Choi, and Soon-Yong Park
Link to presentation

Efficient Generation of Multi-perspective Panoramas
Enliang Zheng, Rahul Raguram, Pierre Fite-Georgel, and Jan-Michael Frahm

 

 

TUESDAY:

Session 1C


Multi-Target Tracking and Segmentation via Discriminative Appearance Model
Guangxia Li, Mingmin Zhang, Yang Li, Zhigeng Pan, and Wenjie Zhang
Link to presentation

Speeding up Cloth Simulation by Linearizing the Bending Function of the Physical Mass-Spring Model
Asmaa A. ElBadrawy and Elsayed E. Hemayed
Link to presentation

Fast and Accurate 3D Scanning using Coded Phase Shifting and High Speed Pattern Projection
Patrick Wissmann, Robert Schmitt, and Frank Forster
Link to presentation

A Feature-preserved Canonical Form for Non-rigid 3D Meshes
Zhouhui Lian and Afzal Godil
Link to presentation

Lightweight 3D Modeling of Urban Buildings from Range Data
Weihong Li, George Wolberg, and Siavash Zokai
Link to presentation

Stereo Matching with Reliable Disparity Propagation
Xun Sun, Xing Mei, Shaohui Jiao, Mingcai Zhou, and Haitao Wang
Link to presentation

 

 

TUESDAY:

Short Paper Poster Presentation


High Quality Computational Integral Imaging Reconstruction using View Synthesis Rendering
Shasha Shi, Patrick Gioia and Gérard Madec

Automatic Semantic Segmentation of 3D Urban Scenes
Federico Tombari and Luigi Di Stefanos

3D Vision Applications for MAVs: Localization and Reconstruction
Andreas Wendel, Michael Maurer, Arnold Irschara, and Horst Bischof

 

WEDNESDAY:

Invited Talk 2

Long QUAN
Professor of the Department of Computer Science and Engineering The Hong
Kong University of Science and Technology

Title: Image-based Modeling

Abstract:  Computer Vision and Computer Graphics meets at Image-base Modeling. In the first part of the talk, I will review the state of the art of the three dimensional reconstruction from images or structure from motion. I will focus on the uncalibrated framework and the quasi-dense approach that we have developed for many years. The quasi-dense approach is unique in that it is the most suitable for building up the object modeling applications. In the second part of the talk, I will present a series of modeling applications from images we have been pursuing in the recent years. I will start with smooth surface modeling from images, then move to the prior-based  hair and tree modeling. I will finish with the most recent building modeling for digital city applications.
Link to presentation

 

 

WEDNESDAY:

Session 2A


Reconstruction and Accurate Alignment of Feature Maps for Augmented Reality
Folker Wientapper, Harald Wuest, and Arjan Kuijper
Link to paper

6DoF Registration of 2D Laser Scans
Benjamin Huhle, Timo Schairer, Andreas Schilling, and Wolfgang Straßer
Link to presentation

Higher Order CRF for Surface Reconstruction from Multi-View Data Sets
Ran Song, Yonghuai Liu, Ralph R. Martin, and Paul L. Rosin
Link to presentation
Video A
Video B

Visual Hull from Imprecise Polyhedral Scene
Peng He and Abbas Edalat
Link to presentation

Hierarchical Shape Matching for Temporally Consistent 3D Video
Chris Budd, Peng Huang, and Adrian Hilton
Link to presentation

Scene Cut: Class-specific Object Detection and Segmentation in 3D Scenes
Jan Knopp, Mukta Prasad, and Luc Van Gool
Link to presentation

A Performance Evaluation of 3D Keypoint Detectors
Samuele Salti, Federico Tombari, and Luigi Di Stefano

 

 

WEDNESDAY:

Session 2B


Human Body Shape Prediction and Analysis Using Predictive Clustering Tree
Pengcheng Xi, Hongyu Guo, and Chang Shu
Link to presentation

Automatic Keypoint Detection on 3D Faces using a Dictionary of Local Shapes
Clement Creusot, Nick Pears, and Jim Austin
Link to presentation

3D Data Segmentation by Local Classification and Markov Random Fields
Federico Tombari and Luigi Di Stefano

Real Time Detection of Repeated Structures in Point Clouds of Urban Scenes
Sam Friedman and Ioannis Stamos
Link to presentation

Multi-scale 3D Feature Extraction and Matching
Hadi Fadaifard and George Wolberg
Link to presentation

An Approach for Shape from Surface Normals with Local Discontinuity Detection
Yilin Wang, Enrique Dunn, and Jan-Michael Frahm

A Performance Evaluation of 3D Keypoint Detection
Primary contact author: Salti, Samuele
Link to presentation

 

 

WEDNESDAY:

Session 2C


Space-time Body Pose Estimation in Uncontrolled Environments
Marcel Germann, Tiberiu Popa, Remo Ziegler, Richard Keiser, and Markus Gross
Link to presentation

A Non-Cooperative Game for 3D Object Recognition in Cluttered Scenes
Andrea Albarelli, Emanuele Rodolà, Filippo Bergamasco, and Andrea Torsello
Link to presentation

Calibration of Nodal and Free-Moving Cameras in Dynamic Scenes for Post-Production
Evren Imre, Jean-Yves Guillemaut, and Adrian Hilton
Link to presentation

Fast Stereo Matching of Feature Links
Chang-Il Kim and Soon-Yong Park
Link to presentation

3D Reconstruction of Interior Wall Surfaces under Occlusion and Clutter
Antonio Adan and Daniel Huber

An Evaluation of Volumetric Interest Points
Tsz-Ho Yu, Oliver J. Woodford, and Roberto Cipolla
Link to presentation

 

WEDNESDAY:

Technical Demonstrations


3D Photo-Realistic Talking Head
Lijuan Wang and Frank Soong

Marker-less Motion Capture using Dense Human-body Shape Scanning System
Koichi Ogawara, Ryo Furukawa, Ryusuke Sagawa, and Hiroshi Kawasaki

Real-time 3D Object Recognition and Tracking Prototype
Limin Shang, Mallory Ketcheson, James McLean, Joseph Lam, and Michael Greenspan

Vehicle Guidance Implemented on a Single-Board Computer
Michael Hödlmoserz, Christoph Bober, and Martin Kampel

A New Ground-based Stereo Panoramic Scanner System
Rongxing Li and Lin Yan

Real-time 3D Video Capturing System Based on Camera Array
Huimin Yu, Gang Yang, Ruigang Yang, Haoji Hu, Ying Zhou, and Jia Wu

On the Optimization and Selection of Local Shape Descriptors
Joseph Lam, Babak Taati, and Michael Greenspan

 

 

THURSDAY:

Session 3A


Sampling Relevant Points for Surface Registration
Andrea Torsello, Emanuele Rodolà, and Andrea Albarelli

Electric Appliance Parts Classification using a Measure Combining the Whole Shape and Local Shape Distribution Similarities
Ryo Hanai, Kimitoshi Yamazaki, Hiroaki Yaguchi, Kei Okada, and Masayuki Inaba
Link to presentation

Procedural 3D Building Reconstruction using Shape Grammars and Detectors
Markus Mathias, Andelo Martinovic, Julien Weissenberg, and Luc Van Gool
Link to presentation

Accurate Estimation of Gaussian and Mean Curvature in Volumetric Images
Erik L. G. Wernersson, Cris L. Luengo Hendriks, and Anders Brun
Link to presentation

Finding the Best Feature Descriptor-Detector Combination
Anders Lindbjerg Dahl, Henrik Aanæs, and Kim Steenstrup Pedersen
Link to presentation

Visual Words for 3D Reconstruction and Pose Computation
Srikrishna Bhat K. K., Marie-Odile Berger, and Frédéric Sur

 

 

THURSDAY:

Session 3B


A Best-Next-View-Selection Algorithm for Multi-View Rendering
Daniel Jung and Reinhard Koch
Link to presentation

3D Human Action Recognition for Multi-View Camera Systems
Michael B. Holte, Thomas B. Moeslund, Nikos Nikolaidis, and Ioannis Pitas
Link to presentation

An Enhanced `Optimization-on-a-Manifold' Framework for Global Registration of 3D Range Data
Francesco Bonarrigo and Alberto Signoroni
Link to presentation

Facade Segmentation in a Multi-View Scenario
Michal Recky, Andreas Wendel, and Franz Leberl
Link to presentation

Stereo Reconstruction of Building Interiors with a Vertical Structure Prior
Bernhard Zeisl, Christopher Zach, and Marc Pollefeys
Link to presentation

Pose Alignment for 3D Models and Single View Stereo Point Clouds Based on Stable Planes
Aitor Aldoma and Markus Vincze
Link to presentation

 

 

THURSDAY:

Session 3C


Image-Space Marker Detection and Recognition using Projective Invariants
Filippo Bergamasco, Andrea Albarelli, and Andrea Torsello

Temporally-Consistent Phase Unwrapping for a Stereo-Assisted Structured Light System
Ricardo R. Garcia and Avideh Zakhor
Link to presentation

A Multi-Camera, Multi-Projector Super-Resolution Framework for Structured Light
Michael Weinmann, Christopher Schwartz, Roland Ruiters, and Reinhard Klein
Link to presentation

Integrating LIDAR into Stereo for Fast and Improved Disparity Computation
Hernán Badino, Daniel Huber, and Takeo Kanade
Link to presentation

Skull Assembly and Completion using Template-based Surface Matching
Li Wei, Wei Yu, Maoqing Li, and Xin Li
Link to presentation

 

THURSDAY:

Invited Talk 3

J P Lewis
Weta Digital

 

Title (tentative): Algorithms and Artistry in Movie Picture Image Modeling

Abstract: Movie visual effects are potentially a showcase application area for algorithms in image modeling and computer vision.  Large effects movies may involve hundreds of person-years of manual artistic effort, and a significant part of this involves the creation of digital reconstructions of filmed objects and environments. The film industry is increasingly tracking and adopting academic research in these areas. This talk will present successful applications of image modeling and related algorithms in movies such as Avatar. The talk will also identify general assumptions that sometimes prevent promising academic research from being easily adopted.