Skip to content

felixmaral/PointNet2-Custom

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PointNet++ (Custom Implementation)

This repository contains a custom implementation of PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space, originally proposed by Charles R. Qi et al: GitHub. The project is developed for educational purposes and as a personal practice project to explore PointNet++ for 3D point cloud segmentation/classification.

Status: The model is fully defined. The project is work in progress.

Current Status

  • ✅ Model architecture implemented end-to-end
  • 🔧 Add dataloaders for multiple file types (e.g., .ply, .bin, .npz, etc.)
  • 🔧 Finalize train.py (training loop, logging, checkpoints, eval)
  • 📚 Complete documentation and usage examples

Notes

  • This code is intended for learning and experimentation; it is not production-ready yet.
  • Interfaces and filenames may change during refactoring.

Original Reference

Qi, C. R., Yi, L., Su, H., & Guibas, L. J. (2017). PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. NeurIPS 2017.
https://arxiv.org/abs/1706.02413

Acknowledgments

All credit for the original method to Charles R. Qi and co-authors. This repository aims to re-implement the core ideas for learning and practice.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages