Anttwo/SCONE
(NeurIPS 2022 - Spotlight) Official code of SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration
This project helps roboticists or drone operators plan efficient paths for their autonomous systems to thoroughly inspect or scan complex 3D environments. By taking 3D models or sensor data of an unknown area as input, it generates optimized trajectories that maximize the surface coverage, ensuring no part of the scene is missed.
No commits in the last 6 months.
Use this if you need to plan a complete scanning or inspection path for a robot or drone in an intricate, unknown 3D space.
Not ideal if you are looking for a fully self-supervised system that learns to explore and reconstruct 3D scenes using only RGB images without ground truth data.
Stars
36
Forks
2
Language
Python
License
MIT
Category
Last pushed
Oct 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Anttwo/SCONE"
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.