6D object pose estimation



The task of estimating the 6D pose of an object (3D translation and 3D rotation) is of great importance for many higher level operations such as robotic manipulation, augmented reality, scene interpretation and autonomous driving. In this workshop, people working on relevant topics in both industry and academia will share up-to-date advances and identify open problems. The workshop will feature several high-quality invited talks, presentations of accepted papers and a challenge on 6D object pose estimation from RGB/RGB-D images.

We invite submissions of 1) papers of unpublished work and 2) extended abstracts of preliminary or already published work. The papers can be long (14 pages excluding references) or short (6 pages excluding references) and will be peer-reviewed. If accepted, the papers will be published in the ECCV workshop proceedings and presented as orals or posters at the workshop. Accepted extended abstracts will be presented as posters. General submission guidelines can be found here. Papers should be submitted to the CMT system and extended abstracts by e-mail to r6d.workshop@gmail.com.

The covered topics include but are not limited to:

Previous workshop editions: 1st edition (ICCV 2015), 2nd edition (ECCV 2016), 3rd edition (ICCV 2017)


08:10invited talk 1 - slides: Federico Tombari (TU Munich), From 3d descriptors to monocular 6D pose: what have we learned?
08:40invited talk 2 - slides: Kostas Bekris (Rutgers University), Towards Robust 6D Pose Estimation: Physics-based Reasoning and Data Efficiency
09:10oral presentations of selected workshop papers (each is 7 min + 1 min for questions)
  1. Image-to-Voxel Model Translation with Conditional Adversarial Networks
    V. Kniaz, F. Remondino
  2. 3D Pose Estimation for Fine-Grained Object Categories
    Y. Wang, Y. Yang, X. Tan, X. Liu, E. Ding, F. Zhou, L. Davis
  3. Seamless Color Mapping for 3D Reconstruction with Consumer-Grade Scanning Devices
    B. Wang, P. Pan, Q. Xiao, L. Luo, X. Ren, R. Jin, X. Jin
  4. Plane-based Humanoid Robot Navigation and Object Model Construction for Grasping
    P. Gritsenko, I. Gritsenko, A. Seidakhmet, B. Kwolek
  5. Category-level 6D Object Pose Recovery in Depth Images
    C. Sahin, T-K Kim
09:50coffee break
10:20invited talk 3 - slides: Bertram Drost (MVTec), Detecting Geometric Primitives in 3D Data
10:50invited talk 4 - slides: Thibault Groueix (Ecole Nationale des Ponts et Chaussées), Parameteric estimation of 3D surfaces and correspondences
11:20BOP: Benchmark for 6D Object Pose Estimation - slides, Tomáš Hodaň (CTU in Prague)
11:40poster session (accepted papers, extended abstracts, invited posters)
12:30lunch break
13:00We recommend attending HANDS 2018, a workshop focused on hand-object interaction and robot grasping/manipulation which includes talks by Andrew Fitzgibbon, Tamim Asfour, Christian Theobalt, Robert Wang and Andrea Tagliasacchi.


Paper submission deadline: July 20th July 27th
Paper acceptance notification: August 14th
Camera-ready submission deadline: September 30th
Extended abstract submission deadline: September 2nd
Workshop date: September 9th


Tomáš Hodaň, Czech Technical University in Prague, hodantom@cmp.felk.cvut.cz
Rigas Kouskouridas, Scape Technologies, rigas@scape.io
Krzysztof Walas, Poznan University of Technology
Tae-Kyun Kim, Imperial College London
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