CVPR 2023 - Vancouver, Canada

C3DV: 1st Workshop on Compositional 3D Vision

First workshop on compositional 3D vision and 3DCoMPaT dataset challenge, hosted by #CVPR2023.


3DCoMPaT Challenge

3DCoMPaT dataset

πŸŽ‰ C3DV 2023 Challenge Winner

The Grounded CoMPaT Recognition (GCR) challenge at CVPR 2023 has come to a close, and we are thrilled to congratulate all the participants for their outstanding engagement and contributions. This challenge has brought together numerous brilliant minds to tackle the complex task of collectively recognizing and grounding compositions of materials on parts of 3D objects using the 3DCoMPaT dataset.

The GCR challenge has been a true testament to the global talent and innovation in the field of computer vision. We appreciate the incredible efforts put forth by all participants, as well as the sponsors and organizers who have made this challenge possible.

The winner of the GCR challenge, sponsored by King Abdullah University of Science and Technology (KAUST), has demonstrated exceptional skill and expertise.


All Tracks 2023 Winner:


Cattalyya Nuengsigkapian

Software Engineer Google AR (Perception)
We are pleased to announce that the winner of both GCR-Coarse and GCR-Fine tracks, Cattalyya Nuengsigkapian, has been awarded a cash prize of $3000.

We extend our warmest congratulations to Cattalyya Nuengsigkapian for her remarkable achievement in the 3DCoMPaT challenge. Her innovative approach and dedication have earned her well-deserved recognition.

You can find Cattalya's video presentation below:

πŸŽ₯  C3DV 2023 Winner Presentation — Cattalyya Nuengsigkapian

And her winning solution repository below:

Cattalya's repository

We commend her remarkable contributions to the challenge goal and look forward to witnessing her future achievements.

Once again, we extend our heartfelt congratulations to the winner, Cattalyya Nuengsigkapian, and all the finalists of the GCR challenge. Your dedication and expertise have truly showcased the potential of compositional 3D vision and its applications. We express our gratitude to all participants for their enthusiasm and commitment to advancing the field of computer vision.

We would also like to thank our sponsors, organizers, and the entire CVPR community for their unwavering support in making this workshop a resounding success. Your contributions have been instrumental in fostering innovation and collaboration in the field of computer vision.

Congratulations to everyone, and we look forward to future challenges and advancements in the exciting field of computer vision!

C3DV Logo KAUST Logo CVPR Logo

Challenge overview

The Grounded CoMPaT Recognition (GCR) is a compositional 3D vision task that aims to collectively recognize and ground compositions of materials on parts of 3D objects. This task is based on the 3DCoMPaT dataset, a large-scale dataset composed of stylized 3D objects and associated 2D renderings.
We propose two variations of this task: GCR-Coarse and GCR-Fine, which are based on coarse-grained and fine-grained 3D segmentations of the 3DCoMPaT models.
We highly encourage participants of the challenge to enter and submit to both tracks of the challenge.

πŸ“Š Dataset

The 3DCoMPaT dataset for both challenge tracks is available through our download page.

πŸ“¨ Submission

Submission will be made through the platform.

πŸ“œ Rules

Here are the rules for the challenge:

  • Submission Limit: Each participant is allowed to submit their solution a maximum of three times per day.
  • Data Usage: Participants are not permitted to use any data other than the 3DCoMPaT data for training their models.
  • Technical Report: Each participant must submit a technical report detailing their methods, which will be made public, in order to be eligible for any prizes or rewards.

πŸ† Awards

Total prize pool: $3000. Teams are encouraged to particpate to both challenge tracks.
Fine track:
  • 1st: $1300
  • 2nd: $700
Coarse track:
  • 1st: $700
  • 2nd: $300

These prizes are designed to motivate participants to put their best effort into the challenge and to reward those who perform exceptionally well. The challenge organizers hope that these prizes will encourage a high level of participation and help to drive innovation in the field of 3D computer vision. It should be noted that eligibility for these prizes is contingent on participants adhering to the rules of the challenge. Therefore, participants must submit their solutions in accordance with the rules and provide a technical report detailing their methods to be considered for any prizes or rewards.

πŸ’¬ Q&A

If you encounter any technical issue related to the challenge, or if you're missing critical information, please open a ticket on our GitHub repository.

Paper submission

Accepted papers

🎯 Accepted papers

We are pleased to present the list of accepted papers for the C3DV workshop at CVPR 2023. These papers showcase the latest research and notable progress made in the field of compositional 3D vision.

We extend our sincere appreciation to all the participants for their valuable contributions to the workshop. The C3DV workshop owes its success to the passion and expertise of these researchers. We cordially invite everyone to explore this curated collection of accepted papers.

🦜 Topics

Besides the CoMPaT challenge, the C3DV workshop also accepts papers in relation with compositional 3D vision. The workshop will include a poster and an oral session for related works. Topics of this workshop include but are not limited to:

  • Deep learning methods for compositional 3D vision
  • Self-supervised learning for compositional 3D vision
  • Visual relationship detection in 3D scenes
  • Zero-shot recognition/detection of compositional 3D visual concepts
  • Novel problems in 3D vision and compositionality
  • Text/composition to 3D generation
  • Text/composition-based editing of 3D scenes/objects
  • Language-guided 3D visual understanding (objects, relationships, ...)
  • Transfer learning for compositional 3D Vision
  • Multimodal pre-training for 3D understanding
  • ...

The submitted 4-page abstracts will be peer-reviewed in CVPR format. Abstracts will be presented in the workshop poster session, and a portion of the accepted papers will be orally presented.


Invited Speakers

Jitendra Malik

Professor University of California, Berkeley

Georgia Gkioxari

Assistant Professor California Institute of Technology

Katerina Fragkiadaki

Assistant Professor Carnegie Mellon University

Matthias Nießner

Professor Technical University of Munich

Angel Xuan Chang

Assistant Professor Simon Fraser University


Workshop Organizers

Wolfgang Heidrich

Professor KAUST

Peter Vajda

Researcher and Engineering Manager Meta AI

Natalia Neverova

Research Lead Meta AI

Mohamed Elhoseiny

Assistant Professor KAUST

Challenge Organizers

Habib Slim

Ph.D. Student KAUST

Mahmoud Ahmed

Research Student KAUST

Mohamed Ayman

Research Student KAUST

Xiang Li

Postdoctoral Researcher KAUST

Yuchen Li

Ph.D. Student KAUST

Peter Wonka

Professor KAUST

Mohamed Elhoseiny

Assistant Professor KAUST



Non-archival track:
Event Date
Paper submission deadline May 31, 2023
Notification to authors June 6, 2023
Camera-ready deadline June 7, 2023
Workshop date June 18, 2023
Event Date
Release of training/validation data April 22, 2023
Validation server online April 22, 2023
Test server online April 22, 2023
Submission deadline June 10, 2023
Fact sheets/source code submission deadline June 12, 2023
Winners announcement June 14, 2023


Workshop Program

All invited talks, oral presentations and the panel discussion will take place in room West 205-206 of the Vancouver Convention Center.
CVPR virtual conference site: (requires CVPR registration).
The day of the workshop is Sunday 18 June 2023. All times are local time (PDT).

For any question or support, please reach @Habib.S. Background image courtesy of @Adi.K.