DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstruction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911988807892992 |
|---|---|
| author | Li, Yanlong Madarasingha, Chamara Thilakarathna, Kanchana |
| author_facet | Li, Yanlong Madarasingha, Chamara Thilakarathna, Kanchana |
| contents | Point cloud streaming is increasingly getting popular, evolving into the norm for interactive service delivery and the future Metaverse. However, the substantial volume of data associated with point clouds presents numerous challenges, particularly in terms of high bandwidth consumption and large storage capacity. Despite various solutions proposed thus far, with a focus on point cloud compression, upsampling, and completion, these reconstruction-related methods continue to fall short in delivering high fidelity point cloud output. As a solution, in DiffPMAE, we propose an effective point cloud reconstruction architecture. Inspired by self-supervised learning concepts, we combine Masked Auto-Encoding and Diffusion Model mechanism to remotely reconstruct point cloud data. By the nature of this reconstruction process, DiffPMAE can be extended to many related downstream tasks including point cloud compression, upsampling and completion. Leveraging ShapeNet-55 and ModelNet datasets with over 60000 objects, we validate the performance of DiffPMAE exceeding many state-of-the-art methods in-terms of auto-encoding and downstream tasks considered. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_03298 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstruction Li, Yanlong Madarasingha, Chamara Thilakarathna, Kanchana Computer Vision and Pattern Recognition Point cloud streaming is increasingly getting popular, evolving into the norm for interactive service delivery and the future Metaverse. However, the substantial volume of data associated with point clouds presents numerous challenges, particularly in terms of high bandwidth consumption and large storage capacity. Despite various solutions proposed thus far, with a focus on point cloud compression, upsampling, and completion, these reconstruction-related methods continue to fall short in delivering high fidelity point cloud output. As a solution, in DiffPMAE, we propose an effective point cloud reconstruction architecture. Inspired by self-supervised learning concepts, we combine Masked Auto-Encoding and Diffusion Model mechanism to remotely reconstruct point cloud data. By the nature of this reconstruction process, DiffPMAE can be extended to many related downstream tasks including point cloud compression, upsampling and completion. Leveraging ShapeNet-55 and ModelNet datasets with over 60000 objects, we validate the performance of DiffPMAE exceeding many state-of-the-art methods in-terms of auto-encoding and downstream tasks considered. |
| title | DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2312.03298 |