ajhamdi/MVTN

pytorch implementation of the ICCV'21 paper "MVTN: Multi-View Transformation Network for 3D Shape Recognition"

/ 100

Emerging

This project helps computer vision researchers and 3D graphics professionals to automatically categorize and retrieve 3D objects with greater accuracy. It takes 3D models (like CAD files or scanned objects) as input and outputs a classification or helps find similar 3D shapes, even when objects are shown from different angles. It is designed for those working with large collections of 3D data who need reliable recognition.

107 stars.

Use this if you are working with 3D object datasets and need to improve the performance of classifying or searching for specific 3D shapes, especially when viewpoint variations are a challenge.

Not ideal if your primary task involves 2D image analysis, generating new 3D models, or if you don't work with explicit 3D mesh or point cloud data.

3D object recognition computer vision research 3D model classification shape retrieval CAD asset management

No License No Package No Dependents

Maintenance 6 / 25

Adoption 9 / 25

Maturity 8 / 25

Community 14 / 25

How are scores calculated?

Stars

107

Forks

Language

Python

License

—

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

Explore ML Frameworks

All categories Trending ML Framework directory Insights