Program

A link to the program booklet.

June 29 (Saturday)

8:45 am - 9:00 am : Welcome

9:00 am - 10:00 am : Keynote 1

• Vladlen Koltun (Stanford University)
  Scene Reconstruction with Commodity Range Cameras

10:00 am - 11:00 am : Oral session 1

Session chair: Edmond Boyer, INRIA Rhone-Alpes

• Real-time 3D Reconstruction in Dynamic Scenes using Point-based Fusion.
  Maik Keller, Pmd technologies; Damien Lefloch, University of Siegen; Martin Lambers, University of Siegen; Shahram Izadi, Microsoft Research Cambridge; Tim Weyrich, University College London; Andreas Kolb, University of Siegen.
   
• Stereo+Kinect for High Resolution Stereo Correspondences.
  Gowri Somanath, University of Delaware; Scott Cohen, Adobe; Brian Price, Adobe; Chandra Kambhamettu.
   
• A Learned Joint Depth and Intensity Prior using Markov Random Fields.
  Daniel Herrera C., University of Oulu; Juho Kannala, University of Oulu; Peter Sturm, INRIA Grenoble; Janne Heikkila, University of Oulu.

11:00 am - 11:15 am : Coffee break

11:15 pm - 12:15 pm : Oral session 2

Session chair: Sameer Agarwal, Google

• The Visual Turing Test for Scene Reconstruction.
  Qi Shan, University of Washington; Riley Adams, UW; Brian Curless, University of Washington; Yasutaka Furukawa, Google Inc.; Steve Seitz, University of Washington.
   
• Creating Georegistered Point Clouds using Geographic Data.
  Chun-Po Wang, Cornell University; Noah Snavely, Cornell University.
   
• Watertight Planar Surface Meshing of Indoor Point-Clouds with Voxel Carving.
  Eric Turner, U. C. Berkeley; Avideh Zakhor, UC Berkeley.

12:15 pm - 1:15 pm : Keynote 2

• Jamie Shotton (Microsoft Research, Cambridge)
  Depth, You, and the World

1:15 pm - 2:30 pm : Lunch break

2:30 pm - 4:30 pm : Posters and Demos 1

Papers

• Real-time 3D Reconstruction in Dynamic Scenes using Point-based Fusion.
  Maik Keller, Pmd technologies; Damien Lefloch, University of Siegen; Martin Lambers, University of Siegen; Shahram Izadi, Microsoft Research Cambridge; Tim Weyrich, University College London; Andreas Kolb, University of Siegen.
   
• The Visual Turing Test for Scene Reconstruction.
  Qi Shan, University of Washington; Riley Adams, UW; Brian Curless, University of Washington; Yasutaka Furukawa, Google Inc.; Steve Seitz, University of Washington.
   
• Online Building Segmentation from Ground-based LiDAR Data in Urban Scenes.
  Jizhou Gao, University of Kentucky; Ruigang Yang, University of Kentucky.
   
• SIFT-Realistic Rendering.
  Dominik Sibbing, RWTH Aachen University; Torsten Sattler, RWTH Aachen University; Bastian Leibe, RWTH Aachen; Leif Kobbelt, RWTH Aachen University.
   
• Omnistereo video textures without ghosting.
  Vincent Couture, Université de Montréal; Michael Langer, McGill University; Sebastien Roy, Université de Montréal.
   
• High-Quality Stereo Video Matching via User Interaction and Space-Time Propagation.
  Chenxi Zhang, University of Kentucky; Brian Price, Adobe; Scott Cohen, Adobe; Ruigang Yang, University of Kentucky.
   
• Automatic Registration of Smooth Object Image to 3D CAD Model for Industrial Inspection Applications.
  Ser Nam Lim, GE Global Research; Li Guan, GE; Shubao Liu, GE Global Research; XIngwei Yang, GE Global Research.
   
• Training-based Object Recognition in Cluttered 3D Point Clouds.
  Guan Pang, Univ of Southern California; Ulrich Neumann, Univ of Southern California.
   
• Deriving Motion Constraints in Finger Joints of Individualized Hand Model for Manipulating by Data Glove.
  Takuya Funatomi, Kyoto university; Takuya Yamane, Kyoto University; Hirotane Ouchida, Kyoto University; Masaaki Iiyama, Kyoto University; Mihcihiko Minoh, Kyoto University.
   
• Statistical Analysis of 3D Faces in Motion.
  Timo Bolkart, Saarland University; Stefanie Wuhrer, Saarland University.
   
• Depth and Intensity based Edge Detection in Time-of-Flight Images.
  Henrik Schäfer, HCI, Heidelberg University; Frank Lenzen; Christoph Garbe.
   
• Evaluation of 3D Feature Descriptors for Multi-modal Data Registration.
  Hansung Kim, University of Surrey; Adrian Hilton, University of Surrey.
   
• Towards Linear-time Incremental Structure from Motion.
  Changchang Wu, Google.
   
• Optimized Aperture for Estimating Depth from Projector's Defocus.
  Hiroshi Kawasaki, Saitama University; Yuki Horita, Kagoshima University; Hitoshi Masuyama, Kagoshima University; Satoshi Ono, Kagoshima University; Makoto Kimura, Yasuo Takane.
   
• Minimal solution for uncalibrated absolute pose problem with a known vanishing point.
  Branislav Micusik, AIT Austrian Institute of Technology; Horst Wildenauer.
   
• On-line Reconstruction of CAD Geometry.
  Klaus Denker, HTWG Konstanz; Daniel Hagel, HTWG Konstanz; Jakob Raible, HTWG Konstanz; Georg Umlauf, HTWG Konstanz; Bernd Hamann, University of California, Davis.
   
• Learning part-based models for animation from surface motion capture.
  Margara Tejera, University of Surrey; Adrian Hilton, University of Surrey.
   
• Synchronized submanifold embedding for robust and real-time capable head pose detection based on range images.
  Matthias Höffken, University of Ulm; Tianyi Wang, Daimler AG; Jürgen Wiest, Ulm University; Ulrich Kreßel, Daimler AG; Klaus Dietmayer, Ulm University.
   
• Detecting Objects in Scene Point Cloud: A Combinational Approach.
  Jing Huang, University of Southern California; Suya You, University of Southern California.
   
• Shape and Reflectance from Scattering in Participating Media.
  Deniz Evrenci, Kyoto University; Masaaki Iiyama, Kyoto University; Takuya Funatomi, Kyoto University; Mihcihiko Minoh, Kyoto University.
   
• Non-rigid registration of depth images using Similarity-invariant differential coordinates.
  Shuntaro Yamazaki, AIST; Satoshi Kagami, AIST; Masaaki Mochimaru, AIST.
   
• Patch Volumes: Segmentation-based Consistent Mapping with RGB-D Cameras.
  Peter Henry, University of Washington; Dieter Fox, University of Washington; Achintya Bhowmik, Intel; Rajiv Mongia, Intel.
   
• A Study of Point Cloud Registration with Probability Product Kernel Functions.
  Hanchen Xiong, University of Innsbruck; Sandor Szedmark, University of Innsbruck; Justus Piater, University of Innsbruck.
   
• Automatic Procedural Modeling of Tree Structures in Point Clouds Using Wavelets.
  Sam Friedman, City University of New York; Ioannis Stamos, City University of New York.

Demos

Industry

• Multi-camera 4D capture, 4D View Solutions.
   
• DLP Lightcrafter based Structured Light Depth Imaging System, Texas Instruments Inc.
   
• Stereo IP Network Camera Demo, Texas Instruments Inc.
   
• 3D Skeletal Hand Tracking, Intel.
   
• Matterport’s system for easy and automatic 3D reconstruction of interior spaces, Matterport.
   
• Geomagic Fuse, 3D Systems Corp.
   
• Modeling the Himalayas from massive image sets, URC Ventures.
   
• Autodesk ReCap: A family of software and services to create intelligent 3D data from photos and laser scans, Autodesk.
   
• Google.

Academia

• PointCraft, Kathleen Tuite and Rahul Banerjee (University of Washington).
   
• SLAM++: Simultaneous Localisation and Mapping at the Level of Objects, Renato F. Salas-Moreno (Imperial College London), Richard A. Newcombe (University of Washington), Hauke Strasdat (Imperial College London), Paul H. J. Kelly (Imperial College London) and Andrew J. Davison (Imperial College London).
   
• Creating Georegistered Point Clouds using Geographic Data, Chun-Po Wang and Noah Snavely (Cornell University).

4:30 pm - 4:40 pm : Break

4:40 pm - 5:40 pm : Oral session 3

Session chair: Philippos Mordohai, Stevens Institute of Technology

• Balloon shapes: reconstructing and deforming objects with volume from images.
  Sara Vicente, Queen Mary, University London; Lourdes Agapito.
   
• X-ray and 3D Data Fusion for 3D Reconstruction of Closed Receptacle Contents.
  Pierluigi Taddei, Joint Research Centre; Vitor Sequeira, Joint Research Centre.
   
• Single View Reconstruction of Peicewise Swept Surfaces.
  Avanish Kushal, University of Washington; Steve Seitz.
   

June 30 (Sunday)

9:00 am - 10:00 am : Keynote 3

• Dieter Fox (University of Washington)
  Depth Cameras and Robotics

10:00 am - 11:00 am : Oral session 4

Session chair: Guy Godin, National Research Council, Canada

• Robust and Accurate One-shot 3D Reconstruction by 2C1P System  with Wave Grid Pattern.
  Nozomu Kasuya, AIST; Ryusuke Sagawa, AIST; Ryo Furukawa; Hiroshi Kawasaki, Saitama University.
   
• 3D Semantic Parameterization for Human Shape Modeling: Application to 3D Animation.
  Christian Rupprecht, Technische Universität München; Olivier Pauly, Technische universität München; Christian Theobalt, Max Planck Institute, Germany; Slobodan Ilic, Technische Universität München.
   
• Interactive Depth-Aware Effects for Stereo Image Editing.
  Josh Abbott, BYU Computer Science; Bryan Morse, Brigham Young University.

11:00 am - 11:15 am : Coffee Break

11:15 am - 12:15 pm : Keynote 4

• Martin Banks (UC Berkeley)
  The Limits of Human Stereopsis in Space and Time

12:15 pm - 1:15 pm : Oral session 5

Session chair: Ruigang Yang, University of Kentucky

• Multi-task Forest for Human Pose Estimation in Depth Images.
  Joe Lallemand, BMW Group; Olivier Pauly, Technische universität München; Loren Schwarz, BMW Group; David Joseph Tan, Technische Universität München; Slobodan Ilic, Technische Universität München.
   
• Personalization and Evaluation of a Real-time Depth-based Full Body Tracker.
  Thomas Helten, MPI Informatik; Andreas Baak, MPI Informatik; Gaurav Bharaj, Harvard University; Meinard Müller, International Audiolabs Erlangen; Hans-Peter Seidel, MPI Informatik; Christian Theobalt, MPI Informatik.
   
• Robust Human Body Shape and Pose Tracking.
  Chun-Hao Huang, Technical University of Munich; Edmond Boyer; Slobodan Ilic, Technische Universität München.

1:15 pm - 2:30 pm : Lunch break

2:30 pm - 4:30 pm : Posters and Demos 2

Posters

• Robust and Accurate One-shot 3D Reconstruction by 2C1P System  with Wave Grid Pattern.
  Nozomu Kasuya, AIST; Ryusuke Sagawa, AIST; Ryo Furukawa; Hiroshi Kawasaki, Saitama University.
   
• 3D Semantic Parameterization for Human Shape Modeling: Application to 3D Animation.
  Christian Rupprecht, Technische Universität München; Olivier Pauly, Technische universität München; Christian Theobalt, Max Planck Institute, Germany; Slobodan Ilic, Technische Universität München.
   
• Multi-task Forest for Human Pose Estimation in Depth Images.
  Joe Lallemand, BMW Group; Olivier Pauly, Technische universität München; Loren Schwarz, BMW Group; David Joseph Tan, Technische Universität München; Slobodan Ilic, Technische Universität München.
   
• Personalization and Evaluation of a Real-time Depth-based Full Body Tracker.
  Thomas Helten, MPI Informatik; Andreas Baak, MPI Informatik; Gaurav Bharaj, Harvard University; Meinard Müller, International Audiolabs Erlangen; Hans-Peter Seidel, MPI Informatik; Christian Theobalt, MPI Informatik.
   
• Robust Human Body Shape and Pose Tracking.
  Chun-Hao Huang, Technical University of Munich; Edmond Boyer; Slobodan Ilic, Technische Universität München.
   
• 3D Face Template Registration Using Normal Maps.
  Zhongjie Wang, MPII; Martin Grochulla; Thorsten Thormählen.
   
• Automatic Rail Extraction in Terrestrial and Airborn Lidar Data.
  Mustafa Mohamad, Queen's University; Kresimir Kusevic, GeoDigital International Inc.; Paul Mrstick, GeoDigital International Inc.; Michael Greenspan, Queen's University.
   
• Measurement of Individual Changes in the Performance of Human Stereoscopic Vision for Disparities at the Limits of the Zone of Comfortable Viewing.
  Jan Paulus, University of Erlangen; Georg Michelson, Department of Ophthalmology, University of Erlangen-Nuremberg, Germany; Marcus Barkowsky, Institut de Recherche en Communications et Cybernétique de Nantes, France.
  Joachim Hornegger, Pattern Recognition Lab, Universtiy of Erlangen-Nuremberg, Germany; Michael Schmidt, Institute of Photonic Technologies, University of Erlangen-Nuremberg, Germany. 
   
• Assisted multi-view stereo reconstruction.
  Matteo Dellepiane, ISTI-CNR; Emanuele Cavarretta, ISTI-CNR; Paolo Cignoni, ISTI-CNR; Roberto Scopigno, ISTI-CNR.
   
• Fast and stable algebraic solution to L₂ three-view triangulation.
  Zuzana Kukelova, CTU in Prague, CMP ; Martin Bujnak, Bzovicka 24, Bratislava, Slovakia; Tomas Pajdla, Prague Technical University.
   
• Shape and Pose Space Deformation for Subject Specific Animation.
  Alexandros Neophytou, University of Surrey; Adrian Hilton, University of Surrey.
   
• Fast and Accurate Calibration of a Kinect Sensor.
  Carolina Raposo, ISR University of Coimbra; Joao Barreto, University of Coimbra; Urbano Nunes.
   
• Object Class Recognition in Mobile Urban Lidar Data Using Global Shape Descriptors.
  Salar Awan, Queen's University; Mustafa Mohamad, Queen's University; Kresimir Kusevic, GeoDigital International Inc.; Paul Mrstick, GeoDigital International Inc.; Michael Greenspan, Queen's University.
   
• Space-time Parameterized Variety Manifolds: A Novel Approach for Arbitrary Multi-perspective 3D View Generation.
  Mansi Sharma, IIT Delhi; Santanu Chaudhury, Indian Institute of Technology Delhi; Brejesh Lall, Indian Institute of Technology Delhi.
   
• 3D Implicit Shape Models using Ray based Hough Voting for Furniture Recognition.
  Jens Wittrowski, Bielefeld University; Agnes Swadzba, Bielefeld University.
   
• Geometric and Color Calibration of Multiview Panoramic Cameras for Life-Size 3D Immersive Video.
  Gregorij Kurillo, UC Berkeley; Harlyn Baker; Zeyu Li, UC Berkeley; Ruzena Bajcsy, University of California, Berkeley.
   
• Direct Shape Recovery from Photometric Stereo with Shadows.
  Roberto Mecca, Technion - IIT; Aaron Wetzler, Technion; Ron Kimmel, Technion; Alfred Bruckstein, Technion.
   
• Evaluation of Methods for Optical 3-D Scanning of Human Pinnas.
  Andreas Reichinger, VRVis Forschungs-GmbH; Piotr Majdak, ; Robert Sablatnig, Vienna University of Technology; Stefan Maierhofer, VRVis Forschungs GmbH.
   
• 3D Object Recognition By Surface Registration of Interest Segments.
  Joseph Lam, Queen's University; Michael Greenspan, Queen's University.
   
• An Iterative Method for Improving Feature Matches.
  Johannes Furch, Fraunhofer HHI; Peter Eisert, Fraunhofer HHI.
   
• Augmented Motion History Volume for Spatiotemporal Editing of 3D Video in Multi-party Interaction Scenes.
  Qun Shi, Kyoto University; Shohei Nobuhara, Kyoto University; Takashi Matsuyama, Kyoto University.
   
• CrowdCam: Instantaneous Navigation of Crowd Images using Angled Graph.
  Aydin Arpa, MIT; Luca Ballan, ETH Zurich; Rahul Sukthankar, Google Research; Gabriel Taubin, Brown University; Marc Pollefeys, ETH Zurich; Ramesh Raskar.
   
• Model-Based Vehicle Pose Estimation and Tracking in Videos Using Random Forests.
  Michael Hödlmoser, Vienna University of Tech.; Branislav Micusik, AIT Austrian Institute of Technology; Marc Pollefeys, ETH Zurich; Ming-Yu Liu, Mitsubishi Electric Research Labs; Martin Kampel, Vienna University of Technology.
   
• Sparse Point Cloud Densification by Combining Multiple Segmentation Methods.
  Michael Hödlmoser, Vienna University of Tech.; Branislav Micusik, AIT Austrian Institute of Technology; Martin Kampel, Vienna University of Technology.

Demos

Industry

• Multi-camera 4D capture, 4D View Solutions.
   
• DLP Lightcrafter based Structured Light Depth Imaging System, Texas Instruments Inc.
   
• Stereo IP Network Camera Demo, Texas Instruments Inc.
   
• 3D Skeletal Hand Tracking, Intel.
   
• Matterport’s system for easy and automatic 3D reconstruction of interior spaces, Matterport.
   
• Geomagic Fuse, 3D Systems Corp.
   
• Modeling the Himalayas from massive image sets, URC Ventures.
   
• Autodesk ReCap: A family of software and services to create intelligent 3D data from photos and laser scans, Autodesk.
   
• Google.

Academia

• PointCraft, Kathleen Tuite and Rahul Banerjee (University of Washington).
   
• SLAM++: Simultaneous Localisation and Mapping at the Level of Objects, Renato F. Salas-Moreno (Imperial College London), Richard A. Newcombe (University of Washington), Hauke Strasdat (Imperial College London), Paul H. J. Kelly (Imperial College London) and Andrew J. Davison (Imperial College London).
   
• 3D Semantic Parameterization for Human Shape Modeling: Application to 3D Animation, Christian Rupprecht (TU Munich), Olivier Pauly (TU Munich), Christian Theobalt (Max Planck Institute, Germany) and Slobodan Ilic (TU Munich).
   
• Augmented Motion History Volume for Spatiotemporal Editing of 3D Video in Multi-party Interaction Scenes, Qun Shi, Shohei Nobuhara and Takashi Matsuyama (Kyoto University).

4:30 pm - 4:40 pm : Break

4:40 pm - 5:40 pm : Keynote 5

• Martin Byröd (Apple Maps)
  Ten Things You Should Know About Large Scale 3D Reconstruction

5:40 pm - 5:50 pm : Closing remarks

7:00 pm : Banquet at the Space Needle