sfu-rsl/graphite
GPU-accelerated nonlinear least squares graph optimization framework
This framework helps robotics and computer vision engineers rapidly solve complex optimization problems, like mapping an environment or adjusting camera views. You define your problem using various constraints on data like sensor readings or image features. It then processes these definitions to output optimized spatial relationships or camera parameters, crucial for applications such as Simultaneous Localization and Mapping (SLAM).
Use this if you need to perform high-speed, non-linear least squares optimization for robotics or computer vision tasks like pose graph optimization or bundle adjustment.
Not ideal if you need a production-ready, stable solution with a guaranteed interface, as this is a research prototype.
Stars
24
Forks
1
Language
C++
License
MIT
Category
Last pushed
Mar 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/sfu-rsl/graphite"
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)