A technology conference booth is showcasing research on SceneFun3D, which focuses on fine-grained functionality and affordance understanding in 3D scenes. The setup includes a wooden partition with vertical slats, behind which a screen displays informative slides on the project. The displayed slide details various aspects of the work, including Functionality Annotations, Natural Language Task Descriptions, and Motion Annotations, with illustrative images and descriptions. To the left, a person operates a laptop placed on a small wooden table, contributing to the interactive nature of the exhibit. In the background, other conference attendees can be seen exploring additional exhibits. The design and setup of the booth highlight an engaging and professional environment aimed at disseminating advanced technological research.
Text transcribed from the image:
Creativity Enrich Life
Inspire Creativity Enry
4444444444
3D Scene Understanding
Open-Vocabulary with Foundation Models
Functionalities & Affordances
SceneFun3D: Fine-grained Functionality and Affordance Understanding in 3D Scenes
Functionality
Annotations
Natural Language
Task Descriptions
hook_turn
hook_pull
hook_turn
key_press
pinch_pull
foot_push
hook_pull
plug_in
tip_push
unplug
Open the oven door
ender
[1] Delitzas et al. "SceneFun3D: Fine-grained Functionality and Affordance Understanding in 3D Scenes CVPR 24
ETH zürich Francis Engelmann
36
2nd Challenge on Open Vocabulary 3D Scene Understanding
Tack 1:30 Object Instance Search
Motion
Annotations
DINEK