This is the code of our paper 'Enhancing Context Models for Point Cloud Geometry Compression With Context Feature Residuals and Multi-Loss'. We used context feature residuals and multi-loss to enhancing Octattenion. It can be used for object point clouds and LiDAR point clouds compression.
python 3.7 PyTorch 1.9.0+cu102 file/environment.sh to help you build this environment
python octAttention.py
python test.py
@ARTICLE{10440338,
author={Sun, Chang and Yuan, Hui and Li, Shuai and Lu, Xin and Hamzaoui, Raouf},
journal={IEEE Journal on Emerging and Selected Topics in Circuits and Systems},
title={Enhancing Context Models for Point Cloud Geometry Compression With Context Feature Residuals and Multi-Loss},
year={2024},
volume={14},
number={2},
pages={224-234},
keywords={Context modeling;Point cloud compression;Probability distribution;Encoding;Solid modeling;Predictive models;Octrees;Geometry point cloud compression;context model;entropy coding;deep learning},
doi={10.1109/JETCAS.2024.3367729}}