Saved in:
Bibliographic Details
Main Authors: Pang, Jiahao, Bui, Kevin, Tian, Dong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.07243
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913231167029248
author Pang, Jiahao
Bui, Kevin
Tian, Dong
author_facet Pang, Jiahao
Bui, Kevin
Tian, Dong
contents The universality of the point cloud format enables many 3D applications, making the compression of point clouds a critical phase in practice. Sampled as discrete 3D points, a point cloud approximates 2D surface(s) embedded in 3D with a finite bit-depth. However, the point distribution of a practical point cloud changes drastically as its bit-depth increases, requiring different methodologies for effective consumption/analysis. In this regard, a heterogeneous point cloud compression (PCC) framework is proposed. We unify typical point cloud representations -- point-based, voxel-based, and tree-based representations -- and their associated backbones under a learning-based framework to compress an input point cloud at different bit-depth levels. Having recognized the importance of voxel-domain processing, we augment the framework with a proposed context-aware upsampling for decoding and an enhanced voxel transformer for feature aggregation. Extensive experimentation demonstrates the state-of-the-art performance of our proposal on a wide range of point clouds.
format Preprint
id arxiv_https___arxiv_org_abs_2402_07243
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point Cloud Compression
Pang, Jiahao
Bui, Kevin
Tian, Dong
Computer Vision and Pattern Recognition
Image and Video Processing
The universality of the point cloud format enables many 3D applications, making the compression of point clouds a critical phase in practice. Sampled as discrete 3D points, a point cloud approximates 2D surface(s) embedded in 3D with a finite bit-depth. However, the point distribution of a practical point cloud changes drastically as its bit-depth increases, requiring different methodologies for effective consumption/analysis. In this regard, a heterogeneous point cloud compression (PCC) framework is proposed. We unify typical point cloud representations -- point-based, voxel-based, and tree-based representations -- and their associated backbones under a learning-based framework to compress an input point cloud at different bit-depth levels. Having recognized the importance of voxel-domain processing, we augment the framework with a proposed context-aware upsampling for decoding and an enhanced voxel transformer for feature aggregation. Extensive experimentation demonstrates the state-of-the-art performance of our proposal on a wide range of point clouds.
title PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point Cloud Compression
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2402.07243