Open☀️3D (original) (raw)
OpenSUN3D
7th Workshop on Open-World 3D Scene Understanding and Representations
September 8/9th in conjunction with ECCV 2026 in Malmö, Sweden.
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.
Keynote Speakers
University of Bristol / Google DeepMind
Paper TrackOpen
| Submission Type | Length | In Proceedings | Deadline | Policies |
|---|---|---|---|---|
| Proceedings Track | 8 pages | Yes | TBD | Anonymous, subject to dual-submission rules. |
| Non-Archival Track | 4 / 8 pages | No | TBD | Anonymous, may include previously published work. |
All submissions must be anonymous and follow theECCV 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: August 5th, 2026
- Notification to authors: August 10th, 2026
- Camera-ready submission: August 15th, 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: TBD
- Notification to authors: TBD
- May include previously published work.
Challenge Track Open
We host a 3-track challenge based on theSceneFun3D benchmark and theArticulate3D dataset. The challenge focuses on fine-grained functionality, affordance, and interaction understanding in 3D indoor environments.
Tracks Overview
- Track 1: Functionality Segmentation (SceneFun3D)
- Track 2: Open-Vocabulary 3D Affordance Grounding (SceneFun3D)
- Track 3: Interaction Understanding (Articulate3D)
Tracks 1 & 2 — SceneFun3D
Resources
Important Dates
- Challenge start: TBD
- Submission deadline: TBD
Track 3 — Articulate3D
Resources
Important Dates
- Submission opens: TBD
- Submission deadline: TBD
Proudly supported by Huawei
