Geometry Grounded Vlm

Extend vision-language models with 3D spatial understanding by adding geometric expert stream alongside semantic expert: predict pixel-aligned 3D point maps, surface normals, and camera poses from 2D images, enabling unified reasoning across 2D semantic and 3D geometric domains.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 9712bd75d4

Frequently asked questions

npx get-skill add adu2021/geometry-grounded-vlm