manycore-research/faceformer
[CVPR 2022] Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
This project helps industrial designers and engineers automatically identify individual surfaces (or "faces") within a complex 3D CAD model when looking at a simple 2D line drawing. You input a 2D wireframe projection of a mechanical object, and it outputs a prediction of which lines belong to which surface, along with 3D reconstructions. This is for professionals working with CAD models who need to quickly understand the underlying 3D structure from simplified drawings.
No commits in the last 6 months.
Use this if you need to interpret 2D wireframe drawings of mechanical parts and automatically identify the distinct faces of the original 3D object.
Not ideal if you are working with photographic images or non-CAD objects, or if you require real-time processing of diverse object types.
Stars
63
Forks
6
Language
Python
License
MIT
Category
Last pushed
May 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/manycore-research/faceformer"
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.