End-to-end learned Lossy Dynamic Point Cloud Attribute Compression
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917753999327232 |
|---|---|
| author | Nguyen, Dat Thanh Zieger, Daniel Stamminger, Marc Kaup, Andre |
| author_facet | Nguyen, Dat Thanh Zieger, Daniel Stamminger, Marc Kaup, Andre |
| contents | Recent advancements in point cloud compression have primarily emphasized geometry compression while comparatively fewer efforts have been dedicated to attribute compression. This study introduces an end-to-end learned dynamic lossy attribute coding approach, utilizing an efficient high-dimensional convolution to capture extensive inter-point dependencies. This enables the efficient projection of attribute features into latent variables. Subsequently, we employ a context model that leverage previous latent space in conjunction with an auto-regressive context model for encoding the latent tensor into a bitstream. Evaluation of our method on widely utilized point cloud datasets from the MPEG and Microsoft demonstrates its superior performance compared to the core attribute compression module Region-Adaptive Hierarchical Transform method from MPEG Geometry Point Cloud Compression with 38.1% Bjontegaard Delta-rate saving in average while ensuring a low-complexity encoding/decoding. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10665 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | End-to-end learned Lossy Dynamic Point Cloud Attribute Compression Nguyen, Dat Thanh Zieger, Daniel Stamminger, Marc Kaup, Andre Image and Video Processing Machine Learning Recent advancements in point cloud compression have primarily emphasized geometry compression while comparatively fewer efforts have been dedicated to attribute compression. This study introduces an end-to-end learned dynamic lossy attribute coding approach, utilizing an efficient high-dimensional convolution to capture extensive inter-point dependencies. This enables the efficient projection of attribute features into latent variables. Subsequently, we employ a context model that leverage previous latent space in conjunction with an auto-regressive context model for encoding the latent tensor into a bitstream. Evaluation of our method on widely utilized point cloud datasets from the MPEG and Microsoft demonstrates its superior performance compared to the core attribute compression module Region-Adaptive Hierarchical Transform method from MPEG Geometry Point Cloud Compression with 38.1% Bjontegaard Delta-rate saving in average while ensuring a low-complexity encoding/decoding. |
| title | End-to-end learned Lossy Dynamic Point Cloud Attribute Compression |
| topic | Image and Video Processing Machine Learning |
| url | https://arxiv.org/abs/2408.10665 |