xieliang555/SFN
Learning to Fill the Seam by Vision: Sub-millimeter Peg-in-hole on Unseen Shapes in Real World
This project helps operations engineers and manufacturing specialists automate delicate assembly tasks like 'peg-in-hole' insertions using robot arms. It takes camera images of pegs and holes as input and guides a robot to precisely insert the peg, even for previously unseen shapes. This allows for reliable automation of fine motor tasks in industrial settings.
No commits in the last 6 months.
Use this if you need to automate precise robotic assembly, especially for varied or custom part geometries, with minimal manual setup.
Not ideal if your peg-in-hole tasks are simple, repetitive, and always involve the exact same shapes, where traditional force-based methods might suffice.
Stars
40
Forks
7
Language
Python
License
—
Category
Last pushed
Jul 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/xieliang555/SFN"
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.