#141141st of 206 in ML frameworks and librariesFor image, video and design, 3d, science, health and research, robotics
pyslam
Visual SLAM framework for mono, stereo and RGBD cameras in Python and C++
- Stars
- 3.4k
- License
- GPL-3.0
- Last commit
- Oct 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
pySLAM is a research framework for visual odometry and SLAM with monocular, stereo and RGBD input. It has a sparse-SLAM core in both Python and C++ (pybind11, with maps interchangeable), plus loop closing, volumetric reconstruction (TSDF, Gaussian splatting), depth prediction and semantic segmentation. It also runs feed-forward 3D inference models such as DUSt3R and VGGT.
Who it is for: Robotics and computer vision researchers prototyping VO/SLAM pipelines
Strengths
- Python and C++ SLAM cores share a map format, so maps load in either
- Many swappable local features, global descriptors and depth models behind one interface
- Reads over 10 dataset types, including KITTI, TUM, EuRoC, ScanNet and ROS bags
- Supports both g2o and GTSAM for graph optimization
Weaknesses
- Install is a long script run that builds OpenCV and many dependencies
- Gaussian splatting and dust3r-based methods require CUDA
- Self-described research framework and work in progress
- Docker only via a third-party repo; Windows needs WSL2
What it needs
- GPU optional
- Needs Python 3.11.9, OpenCV >=4.10, PyTorch >=2.3.1, TensorFlow >=2.13.1, Kornia, Rerun, g2o, GTSAM
- Models: DepthPro, DepthAnythingV2, DepthAnythingV3, RAFT-Stereo, CREStereo
Also in ML frameworks and libraries
See all 206| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | ultralyticsPython library and CLI for training and running YOLO vision models | 94 out of 100 |
| 3 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |