Anttwo/MACARONS
(CVPR 2023) Official code of MACARONS: Mapping And Coverage Anticipation with RGB ONline Self-supervision. Also contains an updated and improved implementation of our previous work SCONE (NeurIPS 2022), on which this work is built.
This project helps autonomous robots or drones efficiently explore and map large, unknown environments in 3D using only color images. It takes raw color video streams as input and generates an optimized path for the robot to follow, along with a detailed 3D reconstruction of the environment. The primary users are robotics engineers, drone operators, and researchers working on autonomous navigation and 3D scene understanding.
No commits in the last 6 months.
Use this if you need an autonomous system to systematically explore and create accurate 3D maps of unfamiliar large spaces without prior knowledge or external supervision.
Not ideal if you require mapping extremely small objects or need highly precise measurements from structured light sensors, as this focuses on broad environmental coverage from color imagery.
Stars
84
Forks
6
Language
Jupyter Notebook
License
—
Category
Last pushed
Dec 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Anttwo/MACARONS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.