Pipeline for 3D Object Detection
- Video → Pointcloud (MASt3R-SLAM)
- Pointcloud → Embedding (SceneScript )
- LLM + request tokens → output 3D object

manycore-research/SpatialLM-Llama-1B · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
https://huggingface.co/manycore-research/SpatialLM-Llama-1B

Seonglae Cho