Final Program


9.30 – 9.40 Welcome and Introduction
9.40 – 10.40
Invited talk by Pushmeet Kohli,
Microsoft Research, UK
Interacting with Humans: Developments in Human Pose Estimation/Gesture Recognition for Kinect
The last few years have seen a tremendous amount of work being done in the development of "natural" user interfaces. These interfaces do not require devices such as keyboards or mice which have been the dominant modes of interaction over the last few decades. An important milestone in the progress of natural user interfaces was the recent launch of Kinect with its unique ability to reliably estimate the pose of the human user in real time. Human pose estimation has been the subject of much research in Computer Vision but only recently, with the introduction of depth cameras and algorithmic advances, has pose estimation made it out of the lab and into the living room. In this talk I will discuss some of my recent work on human pose estimation for Kinect and describe some steps we have taken to make our systems correctly interpret/recognize the intentions of "all" users.
10.40 – 11.00 Coffee break
11.00 – 12.00 Oral session – Sensor Fusion
  Locally Consistent ToF and Stereo Data Fusion
Carlo Dal Mutto (University of Padova), Pietro Zanuttigh (University of Padova), Stefano Mattoccia (University of Bologna), Guido Cortelazzo (University of Padova)

High Accuracy TOF and Stereo Sensor Fusion At Interactive Rates
Rahul Nair (University of Heidelberg), Frank Lenzen (University of Heidelberg), Stephan Meister (University of Heidelberg), Henrik Schaefer (University of Heidelberg), Christoph Garbe (University of Heidelberg), Daniel Kondermann (University of Heidelberg)

A Modular Framework for 2D/3D and Multi-Modal Segmentation and Joint Super-Resolution
Benjamin Langmann (University of Siegen), Klaus Hartmann (University of Siegen), Otmar Loffeld (University of Siegen)

12.00 – 12.10 Short break
12.10 – 12.50 Oral session – Scene Understanding
  Real-Time Plane Segmentation and Obstacle Detection of 3D Point Clouds for Indoor Scenes
Zhe Wang (ICT, CAS), Hong Liu (ICT, CAS), Yueliang Qian (ICT, CAS), Tao Xu (ICT, CAS)

Combining Textural and Geometrical Descriptors for Scene Recognition
Neslihan Bayramoglu (University of Oulu), Janne Heikkilä (University of Oulu), Matti Pietikainen (University of Oulu)

12.50 – 14.30 Lunch break
14.30 – 15.30
Invited talk by Andrew Davison
, Imperial College London
Real-Time SLAM with Moving Cameras
We have seen great advances in real-time 3D vision in recent years, enabled by algorithmic improvements, the continuing increase in commodity processing power and better camera technology. Research in Monocular SLAM (Simultaneous Localisation and Mapping), where a single agile camera moves through a mostly static scene, was for a long time focused on mapping only enough of a scene to enable robust real-time motion estimation of the camera itself. Attention is now turning however to gradually improving the quality of scene reconstruction which can be achieved in real-time. I will speak about how early work on feature-based SLAM is now being surpassed by methods which aim to map dense scene structure, using either standard RGB cameras or depth cameras, and how this is leading towards ever-more general 3D scene modelling and understanding.
15.30 – 16.10 Oral session - Human-Based Analysis
  Human-Centric Indoor Environment Modeling from Depth Videos
Jiwen Lu (ADSC, Singapore), Gang Wang (NTU & ADSC, Singapore)

Human Daily Action Analysis with Multi-View and Color-Depth Data
Zhongwei Cheng (GUCAS), Lei Qin (ICT, CAS), Yituo Ye (GUCAS), Qingming Huang (GUCAS), Qi Tian (UTSA)

16.10 – 16.30 Coffee break
16.30 – 17.50 Oral session – Object Detection & Recognition
  Viewpoint Invariant Matching via Developable Surfaces
Bernhard Zeisl (ETH Zurich), Kevin Koeser (ETH Zurich), Marc Pollefeys (ETH Zurich)

A unified energy minimization framework for model fitting in depth
Carl Ren (University of Oxford), Ian Reid (University of Oxford)

Object Recognition Robust to Imperfect Depth Data
David Fouhey (Carnegie Mellon University), Alvaro Collet (Carnegie Mellon University), Martial Hebert (Carnegie Mellon University), Siddhartha Srinivasa (Carnegie Mellon University)

3D Object Detection with Multiple Kinects
Wandi Susanto (Max Planck Institute), Marcus Rohrbach (Max Planck Institute), Bernt Schiele (Max Planck Institute)

18.05 – 18.15 Closing remarks

Acceptance Rate. We have received 24 high quality papers out of which we have selected 11 for presentation at the workshop. This corresponds to an acceptance rate of 46 %.


Invited Speakers

Pushmeet Kohli

Microsoft Research, UK

Andrew Davison

Imperial College London