Journal article 379 views 59 downloads
An end-to-end dynamic point cloud geometry compression in latent space
,
Guoliang Wang,
Gary Tam ,
Chao Song,
Frederick W.B. Li
Displays, Start page: 102528
Swansea University Author:
Gary Tam
-
PDF | Accepted Manuscript
For the purpose of Open Access the author has applied a CC BY copyright licence to any Author Accepted Manuscript version arising from this submission.
Download (1.43MB)
DOI (Published version): 10.1016/j.displa.2023.102528
Abstract
Dynamic point clouds are widely used for 3D data representation in various applications such as immersive and mixed reality, robotics and autonomous driving. However, their irregularity and large scale make efficient compression and transmission a challenge. Existing methods require high bitrates to...
| Published in: | Displays |
|---|---|
| ISSN: | 0141-9382 |
| Published: |
https://www.easychair.org/smart-program/CGI2023/2023-08-28.html#talk:235847
Elsevier BV
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa64182 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract: |
Dynamic point clouds are widely used for 3D data representation in various applications such as immersive and mixed reality, robotics and autonomous driving. However, their irregularity and large scale make efficient compression and transmission a challenge. Existing methods require high bitrates to encode point clouds since temporal correlation is not well considered. This paper proposes an end-to-end dynamic point cloud compression network that operates in latent space, resulting in more accurate motion estimation and more effective motion compensation. Specifically, a multi-scale motion estimation network is introduced to obtain accurate motion vectors. Motion information computed at a coarser level is upsampled and warped to the finer level based on cost volume analysis for motion compensation. Additionally, a residual compression network is designed to mitigate the effects of noise and inaccurate predictions by encoding latent residuals, resulting in smaller conditional entropy and better results. The proposed method achieves an average 12.09% and 14.76% (D2) BD-Rate gain over state-of-the-art Deep Dynamic Point Cloud Compression (D-DPCC) in experimental results. Compared to V-PCC, our framework showed an average improvement of 81.29% (D1) and 77.57% (D2). |
|---|---|
| Keywords: |
Dynamic point clouds compression, Geometry encoding, Latent scene flow, Deep entropy model |
| College: |
Faculty of Science and Engineering |
| Funders: |
This research was partially supported by Zhejiang Province Natural Science Foundation No. LY21F020013, LY22F020013, the National Natural Science Foundation of China No. 62172366. Gary Tam is supported by the Royal Society grant IEC/NSFC/211159. For the purpose of Open Access the author has applied a CC BY copyright licence to any Author Accepted Manuscript version arising from this submission. |
| Start Page: |
102528 |