News
- [June 17, 2024] The winners of the challenges are announced on this page.
- [June 5, 2024] Updated schedule is available on this page.
- [May 10, 2024] List of accepted papers is available on this page.
- [Jan 22, 2024] Rhobin says hello CVPR'24!
Introduction
Following the success of the first Rhobin workshop at CVPR'23, this second half-day Rhobin workshop will continue providing a venue to present and discuss state-of-the-art research in the reconstruction of human-object interactions from images. The focus of this second workshop will go beyond image-based interaction reconstruction, extend to interaction tracking over time, and seek connections to relevant topics such as egocentric vision and dynamic scene interactions. The second Rhobin challenge will feature five tracks in total with two new tasks on human-object interaction tracking and image-based contact estimation, using two new datasets InterCap and DAMON along with BEHAVE.
Humans are in constant contact with the world as they move through it and interact with it. To better understand how humans interact with the world, it is crucial to estimate human poses, shapes, and movements. 3D Human Pose and Motion estimation from images or videos has attracted a lot of interest. However, in most cases, the task does not explicitly involve objects and the interaction with them. Whether it is 2D detection and/or monocular 3D reconstruction, objects and humans have been mostly studied separately. Considering the interaction between them can marry the best of both worlds.
Participation details of the Rhobin Challenge and paper submission can be found below.
Invited Speakers (Check out the Full Schedule)
 |
 |
 |
|||
Carl Vondrick |
Dima Damen |
Georgios Pavlakos |
|||
| |
Google DeepMind |
|
|||
 |
 |
||||
Angela Dai |
Michael Black |
||||
| |
Meshcapade |
||||
Call for Papers
In this workshop, we invite papers on topics related 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
- 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
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. We also invite 1-page abstract submissions of already published works or relevants works in progress.
Submission Instructions
Submissions are anonymous and should not include any author names, affiliations, and contact information in the PDF.
- Online Submission System: https://cmt3.research.microsoft.com/
- Submission Format: official CVPR template (double column; no more than 8 pages, excluding reference).
Timeline Table (11:59 PM, Pacific Time)
- Full-paper submission deadline: March 20, 2024
- Notification to authors: April 3, 2024
- 1-page Abstract submission deadline: May 15, 2024
- Camera-ready deadline: April 14, 2024
- Workshop: June 17 PM, 2024
Poster Presentation (June 17 3:15-4:00 PM, Pacific Time)
We will provide you with a poster board in our workshop seminar room. The workshop lasts for half a day and you can hang your poster there during that time. We will also have a 45-minute poster session at 3:15-4:00pm PST. We use the same size as the CVPR poster hence you can also use the same poster template here: https://media.eventhosts.cc/Conferences/CVPR2024/cvpr24_poster_template.pptx You can find more information regarding workshop posters here (under Workshop Posters): https://cvpr.thecvf.com/Conferences/2024/PosterPrintingInformation If you encounter any problems, please don't hesitate to contact us at rhobinchallenge@gmail.com.
The Second Rhobin Challenge
Given the importance of human-object interaction, as also highlighted by this workshop, we propose a challenge on reconstructing 3D human and object and estimating 3D human-object and human-scene contact, from monocular RGB images. We have seen promising progress in reconstructing human body mesh or estimating 6DoF object pose from single images. However, most of these works focus on occlusion-free images which are not realistic for settings during close human-object interaction since humans and objects occlude each other. This makes inference more difficult and poses challenges to existing state-of-the-art methods. Similarly, methods estimating 3D contacts have also seen rapid progress, but are restricted to scanned or synthetic datasets, and struggle with generalization to in-the-wild scenarios. In this workshop, we want 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.
Challenge website
- 3D human reconstruction
- 6DoF pose estimation of rigid objects
- Joint reconstruction of human and object
- Video-based tracking
- 3D contact prediction from 2D images
Important dates
- Challenge open: February 5 00:00, 2024 UTC
- Submission deadline: May 30 23:59, 2024 UTC
- Winner award: June 17, 2024
Workshop Organizers
 |
 |
 |
|||
Xi Wang |
Xianghui Xie |
Nikos Athanasiou |
|||
| |
|
|
|||
 |
 |
 |
|||
Kaichun Mo |
Julien Valentin |
Dimitrios Tzionas |
|||
| |
|
|
|||
 |
 |
 |
|||
Otmar Hilliges |
Luc Van Gool |
Gerard Pons-Moll |
|||
| |
|
Max Planck Institute for Informatics, Saarland Informatics Campus |
|||
Challenge Organizers
| |
 |
 |
Xianghui Xie |
Shashank Tripathi |
Ilya A. Petrov |
| |
|
|
 |
|
|
Bharat Lal Bhatnagar |
Dimitrios Tzionas |
Gerard Pons-Moll |
| |
|
Max Planck Institute for Informatics, Saarland Informatics Campus |
Committee Members
Bharat Lal Bhatnagar, Meta, Switzerland
>
Dimitrios Tzionas, University of Amsterdam, Netherlands
Gerard Pons-Moll, University of Tübingen and MPI, Germany
Ilya A. Petrov, University of Tübingen, Germany
Julien Valentin, Microsoft, Switzerland
Kaichun Mo, NVIDIA, USA
Luc Van Gool, ETH Zurich, Switzerland
Nikos Athanasiou, MPI Intelligent System, Germany
Otmar Hilliges, ETH Zurich, Switzerland
Rongyu Chen, National University of Singapore, Singapore
Shashank Tripathi, MPI Intelligent System, Germany
Xianghui Xie, MPI, Germany
Xiaohan Zhang, University of Tübingen, Germany
Xi Wang, ETH Zurich, Switzerland
Yuxuan Xue, University of Tübingen, Germany
Zicong Fan, ETH Zurich, Switzerland
Contact Info
E-mail: rhobinchallenge@gmail.com
Sponsors
The Second RHOBIN Challenge has been generously supported by:
 |
 |
 |
Acknowledgements
Website template borrowed from: https://futurecv.github.io/ (Thanks to Deepak Pathak)