#262 · Primary category： Computer Vision
MonoGS
[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM
Project last updated：08/07/24
GitHub Stars
2.1K
Forks
232
Contributors
6
License
Other
Why we included this project
The first monocular SLAM system built entirely on 3D Gaussian Splatting, MonoGS picked up a CVPR 2024 Highlight and Best Demo Award. It produces dense, photorealistic maps and camera poses in a single framework rather than treating mapping and tracking as separate stages, which is what robots, drones, and mixed-reality headsets need when everything must run in real time from one moving camera. The repo ships runnable configs for monocular, stereo, and RGB-D input, plus scripts that fetch standard benchmarks such as TUM-RGBD, Replica, and EuRoC, so you can compare against known datasets right away. A live mode works with an Intel RealSense depth camera for quick demos on real hardware, and a headless flag logs rendering metrics automatically for anyone benchmarking reconstruction quality or novel-view rendering.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)