Wuziyi616/multi_part_assembly
Code Accompany NeurIPS 2022 Dataset Paper: Breaking Bad. A Shape Assembly Benchmark Implemented in PyTorch
This project helps researchers in computer vision and robotics to assemble 3D shapes from individual parts. It takes in point cloud data representing fragmented objects and outputs the correct rotations and translations needed to reconstruct the original shape. This tool is for academics and engineers working on problems like object reconstruction or robotic assembly.
No commits in the last 6 months.
Use this if you are a researcher developing or benchmarking algorithms for 3D shape assembly from point cloud data.
Not ideal if you need a user-friendly application for everyday 3D modeling or industrial design, as this is a research-focused codebase.
Stars
77
Forks
10
Language
Python
License
MIT
Category
Last pushed
Oct 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Wuziyi616/multi_part_assembly"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
daavoo/pyntcloud
pyntcloud is a Python library for working with 3D point clouds.
yangyanli/PointCNN
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
torch-points3d/torch-points3d
Pytorch framework for doing deep learning on point clouds.
yogeshhk/MidcurveNN
Computation of Midcurve of Thin Polygons using Neural Networks
charlesq34/pointnet2
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space