cambrian-mllm/cambrian-s
Cambrian-S: Towards Spatial Supersensing in Video
This project offers models that dramatically improve how AI systems understand spatial relationships within video footage. It takes raw video data and outputs highly accurate spatial reasoning, enabling AI to better answer questions about object locations, movements, and interactions. This is ideal for researchers and developers building sophisticated video analysis tools, intelligent surveillance, or autonomous systems.
507 stars.
Use this if you need an AI model that can precisely understand where things are and how they move in videos, especially for complex spatial reasoning tasks.
Not ideal if your primary need is general video understanding without a strong focus on intricate spatial details or if you lack development resources to integrate advanced models.
Stars
507
Forks
19
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cambrian-mllm/cambrian-s"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
col14m/cadrille
[ICLR2026] cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
filaPro/cad-recode
[ICCV2025] CAD-Recode: Reverse Engineering CAD Code from Point Clouds
pengsongyou/openscene
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
worldbench/3EED
[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D
Gorilla-Lab-SCUT/PaDT
[ICLR 2026] Official implementation of "Patch-as-Decodable-Token: Towards Unified Multi-Modal...