2nd Call for participants and papers with an extended deadline 

Second Rhobin Challenge – Reconstruction of human-object interaction in conjunction with CVPR 2024, June 2024, Seattle, USA

Website: https://rhobin-challenge.github.io/

Aims and scope 

This half-day workshop will provide a venue to present and discuss state-of-the-art research in the reconstruction of human-object interactions from images. We invite papers on topics related broadly to human-centered interaction modeling. This could include but is not limited to 

• Estimation of 3D human pose and shape from a single image or video

• 3D human motion prediction 

• Interactive motion sequence generation

• Shape reconstruction from a single image

• Object 6-DoF pose estimation and tracking

• Human-centered object semantics and functionality modeling

• Joint reconstruction of both bodies and objects/scenes

• Contact detection/estimation from visual input

• Interaction modeling between humans and objects, e.g., contact, physics properties

• Detection of human-object interaction semantics

• New datasets or benchmarks that have 3D annotations of both humans and objects/scenes.

Participation details of the Rhobin challenge can be found below. 

Submission guidelines 

We invite submissions of a maximum of 8 pages, excluding references, using the CVPR template. Submissions should follow CVPR 2024 instructions. All papers will be subject to a double-blind review process, i.e. authors must not identify themselves on the submitted papers. The reviewing process is single-stage without rebuttals.

• Online Submission System: https://cmt3.research.microsoft.com/Rhobin2024

• Submission Format: CVPR template (double column; no more than 8 pages, excluding reference). Submissions are anonymous and should not include any author names, affiliations, and contact information in the PDF.

If you have any questions, feel free to reach out to us.

Workshop organizers

Xi Wang, ETH Zurich, Switzerland Xianghui Xie, MPI Informatics, Germany

Nikos Athanasiou, MPI Intelligent System, Germany

Ilya Petrov, University of Tübingen, Germany

Kaichun Mo, NVIDIA, USA

Bharat Lal Bhatnagar, Meta, Switzerland

Julien Valentin, Microsoft

Dimitrios Tzionas, University of Amsterdam, Netherlands

Otmar Hilliges, ETH Zurich, Switzerland

Luc Van Gool, ETH Zurich, Switzerland

Gerard Pons-Moll, University of Tübingen and MPI Informatics, Germany

The Second Rhobin Challenge 

We propose a challenge on reconstructing 3D human and object and estimating 3D human-object and human-scene contact, from monocular RGB images. In this workshop, we continue to examine how well the existing human and object reconstruction and contact estimation methods work under more realistic settings and more importantly, understand how they can benefit each other for accurate interaction reasoning. The recently released BEHAVE (CVPR'22), InterCap (GCPR’22) and DAMON (ICCV’23) datasets enable joint reasoning about human-object interactions in real settings and evaluating contact prediction in the wild. We use these datasets in the second Rhobin challenge to spark research in human-object interaction modeling. Challenge winners will be awarded on the day of the workshop. 

Challenge website:
  3D human reconstruction (https://codalab.lisn.upsaclay.fr/competitions/17571)

  6DoF pose estimation of rigid objects (https://codalab.lisn.upsaclay.fr/competitions/17524)

  Joint reconstruction of human and object (https://codalab.lisn.upsaclay.fr/competitions/17522)

  Tracking human-object interaction in a video (https://codalab.lisn.upsaclay.fr/competitions/17572)

  3D contact prediction from RGB images (https://codalab.lisn.upsaclay.fr/competitions/17561)

Challenges are open and more information can be found on the website. 

Important dates 

Challenge open: February 5, 2024

Submission deadline: May 30, 2024

Winner award: June 17/18, 2024

Challenge organizers

Xianghui Xie, MPI Informatics, Germany Shashank Tripathi, MPI Intelligent System, Germany

Dimitrios Tzionas, University of Amsterdam, Netherlands

Gerard Pons-Moll, University of Tübingen and MPI Informatics, Germany