U-Motion: Learned Point Cloud Video Compression with U-Structured Temporal Context Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916657610358784 |
|---|---|
| author | Fan, Tingyu Hu, Yueyu Gong, Ran Wang, Yao |
| author_facet | Fan, Tingyu Hu, Yueyu Gong, Ran Wang, Yao |
| contents | Point cloud video (PCV) is a versatile 3D representation of dynamic scenes with emerging applications. This paper introduces U-Motion, a learning-based compression scheme for both PCV geometry and attributes. We propose a U-Structured inter-frame prediction framework, U-Inter, which performs explicit motion estimation and compensation (ME/MC) at different scales with varying levels of detail. It integrates Top-Down (Fine-to-Coarse) Motion Propagation, Bottom-Up Motion Predictive Coding and Multi-scale Group Motion Compensation to enable accurate motion estimation and efficient motion compression at each scale. In addition, we design a multi-scale spatial-temporal predictive coding module to capture the cross-scale spatial redundancy remaining after U-Inter prediction. We conduct experiments following the MPEG Common Test Condition for dense dynamic point clouds and demonstrate that U-Motion can achieve significant gains over MPEG G-PCC-GesTM v3.0 and recently published learning-based methods for both geometry and attribute compression. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_14501 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | U-Motion: Learned Point Cloud Video Compression with U-Structured Temporal Context Generation Fan, Tingyu Hu, Yueyu Gong, Ran Wang, Yao Computer Vision and Pattern Recognition Image and Video Processing Point cloud video (PCV) is a versatile 3D representation of dynamic scenes with emerging applications. This paper introduces U-Motion, a learning-based compression scheme for both PCV geometry and attributes. We propose a U-Structured inter-frame prediction framework, U-Inter, which performs explicit motion estimation and compensation (ME/MC) at different scales with varying levels of detail. It integrates Top-Down (Fine-to-Coarse) Motion Propagation, Bottom-Up Motion Predictive Coding and Multi-scale Group Motion Compensation to enable accurate motion estimation and efficient motion compression at each scale. In addition, we design a multi-scale spatial-temporal predictive coding module to capture the cross-scale spatial redundancy remaining after U-Inter prediction. We conduct experiments following the MPEG Common Test Condition for dense dynamic point clouds and demonstrate that U-Motion can achieve significant gains over MPEG G-PCC-GesTM v3.0 and recently published learning-based methods for both geometry and attribute compression. |
| title | U-Motion: Learned Point Cloud Video Compression with U-Structured Temporal Context Generation |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2411.14501 |