allenai/ai2thor
An open-source platform for Visual AI.
Provides 200+ photorealistic interactive household scenes with 2600+ annotated objects and physics-based interactions, supporting multiple agent types (navigation, manipulation, drone) and 200+ actions. Built on Unity with rich sensory outputs including RGB, depth, segmentation masks, and metadata—enabling research in embodied AI tasks from navigation to object manipulation. Includes specialized environments (iTHOR for common sense reasoning, ManipulaTHOR for robotic arm control, RoboTHOR for Sim2Real transfer) with domain randomization for materials and lighting.
1,679 stars.
Stars
1,679
Forks
278
Language
C#
License
Apache-2.0
Category
Last pushed
Nov 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/allenai/ai2thor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
VIAME/VIAME
Video and Image Analytics for Multiple Environments
aimh-lab/visione
An AI-powered interactive video retrieval system
instill-ai/console
đŸ“º Instill Console for đŸ”® Instill Core: https://github.com/instill-ai/instill-core
wellflat/imageprocessing-labs
computer vision, image processing and machine learning on the web browser or node.
ZackAkil/video-intelligence-api-visualiser
A simple app that lets you visualise annotations from the Google Cloud Video Intelligence API...