6D object pose estimation



Estimation of 6D object pose is of great importance to many higher level tasks such as robotic manipulation (Amazon Picking Challenge), scene interpretation and augmented reality. The workshop will feature several high-quality invited talks, presentations of accepted papers, a panel discussion to identify open problems, and a challenge with the goal of establishing the state of the art in 6D object pose estimation from RGB or RGB-D images.

We invite submissions of 1) papers of unpublished work and 2) extended abstracts of preliminary or already published work. The papers will be peer-reviewed and, if accepted, published in the ICCV workshop proceedings (submission guidelines, submission system for papers, extended abstracts should be submitted to r6d.workshop@gmail.com). Accepted submissions will be presented as orals/posters/spotlights at the workshop. The covered topics include but are not limited to:

We invite submissions of results to the SIXD Challenge 2017. We have defined an evaluation protocol and identified a set of datasets which are provided in a unified format. The results will be announced during the workshop and the authors of the winning methods will be invited to present their approaches. A paper with an analysis of the collected results will be published after the workshop.

Previous workshop editions: 1st edition (ICCV 2015), 2nd edition (ECCV 2016)


08:30 - 08:40opening
08:40 - 09:10invited talk 1: Object Detection for Robotics, Stefan Hinterstoisser​ (Google X)
09:10 - 09:40invited talk 2: Geometry and Learning in 3D Correspondence Problems, Alex Bronstein (Technion, Intel, TAU)
09:40 - 10:15spotlight presentations of selected accepted papers (7 min each):
  1. Deep Learning of Convolutional Auto-encoder for Image Matching and 3D Object Reconstruction in the Infrared Range
    V. Knyaz, O. Vygolov, V. Kniaz, Y. Vizilter, V. Gorbatsevich, T. Luhmann, N. Conen
  2. Efficient and Accurate Registration of Point Clouds with Plane to Plane Correspondences
    K. Khoshelham, W. Foerstner
  3. 3D Pose Regression using Convolutional Neural Networks
    S. Mahendran, H. Ali, R. Vidal
  4. Propagation of Orientation Uncertainty of 3D Rigid Object to Its Points
    M. Franaszek, G. Cheok
  5. Mutual Hypothesis Verification for 6D Pose Estimation of Natural Objects
    K. Park, J. Prankl, M. Vincze
10:15 - 11:00coffee break
11:00 - 11:30invited talk 3: Tracking, Pose Estimation and Dancing Hot Dogs, Edward Rosten (Snap Inc.)
11:30 - 12:00invited talk 4: Predicting Voxel-based Reconstructions of Objects, David Fouhey (UC Berkeley)
12:00 - 12:30SIXD challenge results and awards, Tomáš Hodaň
12:30 - 14:00lunch break
14:00 - 15:00oral presentations of selected accepted papers (15 min each):
  1. Introducing MVTec ITODD - A Dataset for 3D Object Recognition in Industry
    B. Drost, M. Ulrich, P. Bergmann, P. Härtinger, C. Steger
  2. Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulk
    R. Brégier, F. Devernay, L. Leyrit, J. Crowley
  3. Combined Holistic and Local Patches for Recovering 6D Object Pose
    H. Zhang, Q. Cao
  4. Multi-view 6D Object Pose Estimation and Camera Motion Planning using RGBD Images
    J. Sock, S. Kasaei, L. Lopes, T.-K. Kim
15:00 - 15:45poster session (accepted papers, extended abstracts, invited posters)
15:45 - 16:30coffee break
16:30 - 17:00invited talk 5: Lifting Object Detection Datasets into 3D, Lourdes Agapito (University College London)
17:00 - 17:10Presentation of the winning method in the SIXD Challenge 2017
17:10 - 17:206D at Scape AR
17:20 - 18:00discussion, closing


Paper submission deadline: August 1st August 8th
Paper acceptance notification: August 15th August 18th
Camera-ready submission deadline: August 24th
Extended abstract submission deadline: October 8th
The SIXD Challenge submission deadline: October 1st October 8th
Workshop date: October 29th


Krzysztof Walas, Poznan University of Technology, krzysztof.walas@put.poznan.pl
Tomáš Hodaň, Czech Technical University in Prague, hodantom@cmp.felk.cvut.cz
Tae-Kyun Kim, Imperial College London, tk.kim@imperial.ac.uk
Jiří Matas, Czech Technical University in Prague
Carsten Rother, Heidelberg University
Frank Michel, Technical University Dresden
Vincent Lepetit, Technical University Graz
Ales Leonardis, University of Birmingham
Carsten Steger​, Technical University of Munich, MVTec
Caner Sahin, Imperial College London
Rigas Kouskouridas, Scape




Scape AR   Osaro