6D object pose estimation

Program

13:30Opening, SLIDES
13:40Invited talk 1: Slobodan Ilic (TU Munich, Siemens AG), Domain Adaptation for 6D Object Pose Recovery from Synthetic Data
14:10Invited talk 2: Eric Brachmann (Heidelberg University), Robust Pose Optimization Made Differentiable, SLIDES, PHOTO
14:40Oral presentations of workshop papers (each is 6 min + 1 min for questions)
  1. CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation, PDF
    Kartik Gupta, Lars Petersson, Richard Hartley
  2. CorNet: Generic 3D Corners for 6D Pose Estimation of New Objects without Retraining, PDF
    Giorgia Pitteri, Vincent Lepetit, Slobodan Ilic
  3. Unsupervised Joint 3D Object Model Learning and 6D Pose Estimation for Depth-Based Instance Segmentation, PDF
    Yuanwei Wu, Tim K Marks, Anoop Cherian, Siheng Chen, Chen Feng, Guanghui Wang, Alan Sullivan
  4. An Annotation Saved is an Annotation Earned: Using Fully Synthetic Training for Object Detection, PDF
    Stefan Hinterstoisser, Olivier Pauly, Hauke Heibel, Martina Marek, Martin Bokeloh
  5. HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects, PDF
    Roman Kaskman, Sergey Zakharov, Ivan Shugurov, Slobodan Ilic
  6. A Refined 3D Pose Dataset for Fine-Grained Object Categories, PDF
    Yaming Wang, Yi Yang
  7. Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinement, PDF
    Bo Chen, Jiewei Cao, Alvaro Parra, Tat-Jun Chin
15:30Coffee break
16:00Invited talk 3: Vincent Lepetit (Uni. de Bordeaux), 3D Pose Estimation and 3D Model Retrieval for Objects in the Wild, SLIDES
16:30Invited talk 4: Matthias Nießner (TU Munich), 9DOF Scan2CAD Alignment in 3D Scans, SLIDES
17:00Results of the BOP Challenge 2019: Tomáš Hodaň (CTU in Prague), SLIDES, SLIDES (short version)
17:20Awards, discussion, closing
17:30Poster session (workshop papers, extended abstracts, invited posters)

News

Introduction

Accurate estimation of the 6D pose of an object (3D translation and 3D rotation) is of great importance to many higher level tasks such as robotic manipulation, augmented reality and autonomous driving.

The introduction of consumer and industrial grade RGB-D sensors and the advent of deep learning have allowed for substantial improvement in 6D object pose estimation. However, there still remain challenges to be addressed such as robustness against occlusion and clutter, scalability to multiple objects, effective synthesis of training data, and fast and reliable object modelling, including capturing of reflectance properties. Extending contemporary methods to work reliably and with sufficient execution speed in an industrial setting is still an open problem. Many recent methods focus on specific rigid objects, but pose estimation of deformable or articulated objects and of object categories is also an important research direction.

In this workshop, people working on relevant topics in both academia and industry will share up-to-date advances and identify open problems. The workshop will feature several high-quality invited talks, presentations of accepted workshop papers and a challenge on 6D object pose estimation from RGB/RGB-D images.

Previous workshop editions: 1st edition (ICCV 2015), 2nd edition (ECCV 2016), 3rd edition (ICCV 2017), 4th edition (ECCV 2018).

A Summary of the 4th International Workshop on Recovering 6D Object Pose.

BOP Challenge 2019

We invite submissions to the BOP Challenge 2019.

Workshop Papers

We invite submissions of 1) papers of unpublished work and 2) extended abstracts of preliminary or already published work. The papers (8 page limit) will be peer-reviewed. If accepted, the papers will be published in the ICCV workshop proceedings, which will be archived in the IEEE Xplore Digital Library and the CVF Open Access, and presented as orals or posters at the workshop. Accepted extended abstracts will be presented as posters (the size of panels is 1950mm (width) x 950mm, i.e. the same as for the main conference). The workshop paper format follows the one of the main conference. 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:

Dates

Paper submission deadline: August 2, August 11, 2019 (11:59PM PST)
Paper acceptance notification: August 23, 2019
Camera-ready submission deadline: August 29, 2019 (11:59PM PST)
Deadline for submissions to the BOP Challenge 2019: October 14, October 21, 2019 (11:59PM PST)
Extended abstract submission deadline: October 21, 2019
Workshop date: October 28, 2019

Organizers

Tomáš Hodaň, Czech Technical University in Prague, hodantom@cmp.felk.cvut.cz
Rigas Kouskouridas, Scape Technologies, rigas@scape.io
Tae-Kyun Kim, Imperial College London
Jiří Matas, Czech Technical University in Prague
Carsten Rother, Heidelberg University
Vincent Lepetit, Universite de Bordeaux
Ales Leonardis, University of Birmingham
Krzysztof Walas, Poznan University of Technology
Carsten Steger​, Technical University of Munich, MVTec
Eric Brachmann, Heidelberg University
Bertram Drost, MVTec
Juil Sock, Imperial College London

Contact

r6d.workshop@gmail.com