jmanhype/vggt-mps
VGGT 3D Vision Agent optimized for Apple Silicon with Metal Performance Shaders
This tool helps 3D artists, architects, or engineers transform collections of images into detailed 3D models. You feed it multiple photographs of an object or scene from different angles, and it generates depth maps, camera positions, and a precise 3D point cloud reconstruction. It's designed for anyone needing to create accurate 3D representations from real-world photos using an Apple Silicon Mac.
Use this if you need to create accurate 3D reconstructions (depth maps, camera poses, point clouds) from multiple images and you work on an Apple Silicon Mac.
Not ideal if you need to run this on non-Apple hardware (like Windows or Linux with NVIDIA GPUs) or require support for lower-precision floating-point numbers.
Stars
87
Forks
8
Language
Python
License
MIT
Category
Last pushed
Mar 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/jmanhype/vggt-mps"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
alicevision/AliceVision
3D Computer Vision Framework
colmap/colmap
COLMAP - Structure-from-Motion and Multi-View Stereo
ANTsX/ANTs
Advanced Normalization Tools (ANTs)
alicevision/Meshroom
Node-based Visual Programming Toolbox
MOLAorg/mola
A Modular Optimization framework for Localization and mApping (MOLA)