OpenSUN3D

6th Workshop on Open-World 3D Scene Understanding and Representations

in conjunction with CVPR in Colorado, USA.

Introduction

For intelligent agents to thrive in the physical world, they must not only perceive but also comprehend and act within it. This year’s workshop unites leading researchers advancing world models and spatial intelligence, from 3D perception and scene understanding to generative world representations. Through keynotes and a challenge on open 3D interaction perception, we will explore how machines learn to reason about and engage with their environments. The workshop aims to shape the next generation of spatially grounded AI, bridging scientific discovery, practical deployment, and responsible innovation.

Important Dates

Challenge

Challenges Open

Paper Track

Paper Submissions Open

Paper Track

Proceedings Track Deadline

Paper Track

Non-Archival Track Deadline

Challenge

Challenges Deadline

Workshop

Workshop

Next deadline:

Keynote Speakers

Tali Dekel is an Associate Professor at the Faculty of Mathematics and Computer Science at the Weizmann Institute of Science, and a Staff Research Scientist at Google DeepMind. Before that she was a Postdoctoral Associate with Prof. Bill Freeman, at CSAIL, MIT. She completed her Ph.D. in the school of Electrical Engineering of Tel-Aviv University, where she was supervised by Prof. Shai Avidan (TAU) and Prof. Yael Moses (IDC). Her main research interests include images and videos analysis, multi-view systems, 3D structure and motion estimation, image synthesize and rendering.


Djamila Aouada is an Associate Professor at the University of Luxembourg (UL) and the Deputy Director of the Interdisciplinary Centre for Security, Reliability and Trust (SnT). She leads the Computer Vision, Imaging and Machine Intelligence (CVI²) research group, focusing on advancing research in Computer Vision and Machine Learning with emphasis on real-world applications through industrial collaborations.



Aleksander Holynski is a research scientist at Google DeepMind and a professor at Columbia University. Previously, he was a postdoctoral scholar at UC Berkeley (BAIR) working with Alyosha Efros and Angjoo Kanazawa. He did his PhD at the University of Washington, advised by Steve Seitz, Brian Curless, and Rick Szeliski and received his B.S. at the University of Illinois at Urbana-Champaign.


Chelsea Finn is an Assistant Professor in Computer Science and Electrical Engineering at Stanford University and co-founder of Pi. Her lab, IRIS, studies intelligence through robotic interaction at scale, and is affiliated with SAIL and the ML Group. She is interested in the capability of robots and other agents to develop broadly intelligent behavior through learning and interaction. Previously, she completed her Ph.D. in computer science at UC Berkeley and her B.S. in electrical engineering and computer science at MIT.


Andrea Tagliasacchi is an Associate Professor at Simon Fraser University (Vancouver, Canada), where he holds the Visual Computing Research Chair within the School of Computing Science. He is also an Associate Professor in the Department of Computer Science at the University of Toronto. Before joining SFU, Andrea spent several years as a researcher at Google. Prior to that, he was an Assistant Professor at the University of Victoria (2015–2018), where he held the Industrial Research Chair in 3D Sensing, jointly sponsored by Google and Intel. Andrea’s academic background includes a postdoctoral fellowship at EPFL, a PhD from Simon Fraser University (as an NSERC Alexander Graham Bell Fellow), and an MSc from Politecnico di Milano, where he graduated as a gold medalist. His research focuses on 3D visual perception, a field that bridges computer vision, computer graphics, and machine learning.

Paper Track Open

Submission Type Length In Proceedings Deadline Policies
Proceedings Track 8 pages Yes Mar 15, 2026 Anonymous, subject to dual-submission rules.
Non-Archival Track 4 / 8 pages No Apr 20, 2026 Anonymous, may include previously published work.
Submit via OpenReview

All submissions must be anonymous and follow the CVPR 26 author guidelines.

Submission Deadline 1:
Proceedings Track

8-page full papers for inclusion in the CVPR workshop proceedings. Those submissions are subject to the dual submission policy, only original work not under review or published elsewhere is allowed.

  • Submission deadline: March 15, 2026 (23:59 GMT)
    Countdown:
  • Notification to authors: March 18, 2026
  • Camera-ready submission: April 10, 2026

Submission Deadline 2:
Extended Abstracts & Non-Archival Papers

4-page extended abstracts or 8-page full papers that will not be included in the proceedings. May include previously published work that the authors want to present at the workshop.

  • Submission deadline: April 20, 2026 (23:59 GMT)
    Countdown:
  • Notification to authors: April 25, 2026
  • May include previously published work.

Challenge Track Open

We host a 3-track challenge based on the SceneFun3D benchmark and the Articulate3D dataset. The challenge focuses on fine-grained functionality, affordance, and interaction understanding in 3D indoor environments.

Tracks Overview


Tracks 1 & 2 — SceneFun3D

Resources

Important Dates

  • Challenge start: Jan 15, 2026
  • Submission deadline: May 29, 2026

Track 3 — Articulate3D

Resources

Important Dates

  • Submission opens: Jan 15, 2026
  • Submission deadline: May 29, 2026

Organizers