PCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913437735452672 |
|---|---|
| author | Mao, Xiaolong Yuan, Hui Lu, Xin Hamzaoui, Raouf Gao, Wei |
| author_facet | Mao, Xiaolong Yuan, Hui Lu, Xin Hamzaoui, Raouf Gao, Wei |
| contents | Learning-based methods have proven successful in compressing geometric information for point clouds. For attribute compression, however, they still lag behind non-learning-based methods such as the MPEG G-PCC standard. To bridge this gap, we propose a novel deep learning-based point cloud attribute compression method that uses a generative adversarial network (GAN) with sparse convolution layers. Our method also includes a module that adaptively selects the resolution of the voxels used to voxelize the input point cloud. Sparse vectors are used to represent the voxelized point cloud, and sparse convolutions process the sparse tensors, ensuring computational efficiency. To the best of our knowledge, this is the first application of GANs to compress point cloud attributes. Our experimental results show that our method outperforms existing learning-based techniques and rivals the latest G-PCC test model (TMC13v23) in terms of visual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05677 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression Mao, Xiaolong Yuan, Hui Lu, Xin Hamzaoui, Raouf Gao, Wei Image and Video Processing 94J20 I.4.2 Learning-based methods have proven successful in compressing geometric information for point clouds. For attribute compression, however, they still lag behind non-learning-based methods such as the MPEG G-PCC standard. To bridge this gap, we propose a novel deep learning-based point cloud attribute compression method that uses a generative adversarial network (GAN) with sparse convolution layers. Our method also includes a module that adaptively selects the resolution of the voxels used to voxelize the input point cloud. Sparse vectors are used to represent the voxelized point cloud, and sparse convolutions process the sparse tensors, ensuring computational efficiency. To the best of our knowledge, this is the first application of GANs to compress point cloud attributes. Our experimental results show that our method outperforms existing learning-based techniques and rivals the latest G-PCC test model (TMC13v23) in terms of visual quality. |
| title | PCAC-GAN: A Sparse-Tensor-Based Generative Adversarial Network for 3D Point Cloud Attribute Compression |
| topic | Image and Video Processing 94J20 I.4.2 |
| url | https://arxiv.org/abs/2407.05677 |