The image captures a scene from a tech exhibition or conference, featuring a presentation on "SceneFun3D: Fine-grained Functionality and Affordance Understanding in 3D Scenes." A flat-screen monitor is mounted on a wooden slat wall, displaying detailed information about the functionality annotations, natural language task descriptions, and motion annotations used in the project. The monitor shows diagrams and examples of actions such as "hook_turn," "plug_in," "unplug," and a natural language task description prompting to "Open the oven door." Below the screen, perched on a small wooden shelf, is a laptop that appears to be connected to the monitor, displaying supplementary content related to the presentation. To the right, a person in a blue T-shirt is partially visible, possibly engaged with the exhibit. The setting is an open space with other attendees and exhibitors in the background, suggesting a busy and interactive environment dedicated to showcasing advancements in technology.
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