Sparse Tensor-based point cloud attribute compression using Augmented Normalizing Flows

Tzu Po Lin, Monyneath Yim, Jui Chiu Chiang, Wen Hsiao Peng, Wen Nung Lie

研究成果: Conference contribution同行評審

摘要

The large amount of data of point cloud poses challenges for efficient storage and transmission. To address this problem, various learning-based techniques, in addition to rule-based solutions, have been developed for point cloud compression. While many previous works employed the variational autoencoder (VAE) structure, they have failed to achieve promising performance at high bitrates. In this paper, we propose a novel point cloud attribute compression technique based on the Augmented Normalizing Flow (ANF) model, which incorporates sparse convolutions where a sparse tensor is used to represent the point cloud attribute. The invertibility of the NF model provides better reconstruction compared to VAE-based coding schemes. ANF provides a more flexible way to model the input distribution by introducing additional conditioning variables into the flow. Not only comparable to G-PCC, the experimental results demonstrate the effectiveness and superiority of the proposed method over several learning-based point cloud attribute compression techniques, even without requiring sophisticated context modeling.

原文English
主出版物標題2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1739-1744
頁數6
ISBN(電子)9798350300673
DOIs
出版狀態Published - 2023
事件2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 - Taipei, Taiwan
持續時間: 31 10月 20233 11月 2023

出版系列

名字2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

Conference

Conference2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
國家/地區Taiwan
城市Taipei
期間31/10/233/11/23

指紋

深入研究「Sparse Tensor-based point cloud attribute compression using Augmented Normalizing Flows」主題。共同形成了獨特的指紋。

引用此