UT-Austin-RPL/FORGE
Code for Few-View Object Reconstruction with Unknown Categories and Camera Poses at 3DV 2024 (oral)
FORGE helps computer vision researchers and robotics engineers reconstruct 3D shapes of objects from a small number of 2D images. You provide a few images of an object, and it outputs a complete 3D model of that object, even if the object type and camera angles aren't known beforehand. This is ideal for quickly creating 3D models from limited visual data.
No commits in the last 6 months.
Use this if you need to generate a 3D model of an object from just a few pictures, especially when you don't know the exact object category or how the pictures were taken.
Not ideal if you're looking for a solution that performs well with real-world images under strong or unusual lighting conditions, as its performance may degrade.
Stars
93
Forks
9
Language
Python
License
—
Category
Last pushed
Jan 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/UT-Austin-RPL/FORGE"
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.