INSAIT will co-organize the OpenSUN3D Workshop at the International Conference on Computer Vision (ICCV) 2025, in collaboration with researchers from Stanford University, ETH Zürich, Google, NVIDIA, Microsoft, and the Technical University of Munich. The workshop will focus on advancing open-vocabulary and open-world understanding of 3D scenes, a critical direction for the future of artificial intelligence and computer vision.
This is the second workshop co-organized by INSAIT at ICCV 2025. OpenSUN3D will explore how foundation models can bridge 2D and 3D vision with language, while addressing challenges in understanding functionality, affordance, materials, and interactions within 3D environments.
The workshop will feature three challenge tracks: Functionality Segmentation (SceneFun3D), Affordance Grounding (SceneFun3D), and Interaction Understanding. The third track is hosted by INSAIT and is based on the institute’s upcoming ICCV paper, Articulate3D.
Researchers and practitioners in computer vision, robotics, and AI are invited to submit 4-page extended abstracts to the paper track. The submission deadline is September 1, 2025.
The event will also include keynote presentations from leading experts at Google DeepMind, Stanford University, Simon Fraser University, Apple, and New York University.
Further details and participation guidelines are available at: https://lnkd.in/dTRzP-ug