The 4D Vision Workshop will be held in conjunction with ECCV'20 in Glasgow, Scotland.

Visual scene understanding is crucial for many practical applications in the real world. A lot of work has focused on 3D scene analysis. Considering the scene also in time, i.e. 4D visual understanding, is key for holistic understanding of the surrounding world. 3D scene analysis, 3D reconstruction, SLAM and others focus on the scene primarily without dynamic objects. At the same time video analysis has provided very advanced methods for understanding visual information in time.

Recent research e.g. in perception for autonomous driving or embodied vision, have also started to consider both aspects of scene analysis. Gleaning insights from scene understanding, video analysis, and 3D modeling and sensing in the realms of both dynamic and static scenes, we hope to shed more light on the topic of 4D vision for scene understanding.

Invited Speakers

Raquel Urtasun

University of Toronto

Uber ATG

Michael Ryoo

Stoneybrook University

Google Research

Marc Pollefeys

ETH Zurich

Microsoft MR&AI Lab Zurich

Thomas Funkhouser

Princeton University

Google Research

Xiaolong Wang

UC San Diego


Topics include, but are not limited to:

  • 3D scene understanding

  • Perception for autonomous driving

  • Ego-centric scene understanding

  • Sequence models for scene analysis

  • Video understanding

  • 3D sensing of moving objects

We will invite submissions of extended abstracts (2-4 pages) through CMT. All accepted abstracts will present a poster at the workshop. A subset of the abstracts will be selected for a spotlights session, where each will present a short oral presentation. More information will follow soon.

Program and Important Dates

  • Submission Deadline: TBD.

  • Notification of Acceptance: TBD.

  • Camera-ready Deadline: TBD.

  • Workshop: Sunday 23 August 2020 or Friday 28 August 2020.

More information will follow soon.

Program Committee



For any questions about the workshop, please contact