An End-to-end Dynamic Point Cloud Geometry Compression in Latent Space
Jiang, Zhaoyi; Wang, Guoliang; Tam, Gary K. L.; Song, Chao; Yang, Bailin; Li, Frederick W. B.
Gary K. L. Tam
Dr Frederick Li email@example.com
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).
Jiang, Z., Wang, G., Tam, G. K. L., Song, C., Yang, B., & Li, F. W. B. (in press). An End-to-end Dynamic Point Cloud Geometry Compression in Latent Space. Displays, https://doi.org/10.1016/j.displa.2023.102528
|Journal Article Type||Article|
|Acceptance Date||Aug 28, 2023|
|Online Publication Date||Sep 14, 2023|
|Deposit Date||Sep 12, 2023|
|Publicly Available Date||Sep 20, 2023|
|Peer Reviewed||Peer Reviewed|
Accepted Journal Article
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.
You might also like
A Mixed Reality Training System for Hand-Object Interaction in Simulated Microgravity Environments
C2SPoint: A classification-to-saliency network for point cloud saliency detection
Gamifying Experiential Learning Theory
IAACS: Image Aesthetic Assessment Through Color Composition And Space Formation