MOC-RVQ: Multilevel Codebook-Assisted Digital Generative Semantic Communication
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912048812654592 |
|---|---|
| author | Zhou, Yingbin Sun, Yaping Chen, Guanying Xu, Xiaodong Chen, Hao Huang, Binhong Cui, Shuguang Zhang, Ping |
| author_facet | Zhou, Yingbin Sun, Yaping Chen, Guanying Xu, Xiaodong Chen, Hao Huang, Binhong Cui, Shuguang Zhang, Ping |
| contents | Vector quantization-based image semantic communication systems have successfully boosted transmission efficiency, but face challenges with conflicting requirements between codebook design and digital constellation modulation. Traditional codebooks need wide index ranges, while modulation favors few discrete states. To address this, we propose a multilevel generative semantic communication system with a two-stage training framework. In the first stage, we train a high-quality codebook, using a multi-head octonary codebook (MOC) to compress the index range. In addition, a residual vector quantization (RVQ) mechanism is also integrated for effective multilevel communication. In the second stage, a noise reduction block (NRB) based on Swin Transformer is introduced, coupled with the multilevel codebook from the first stage, serving as a high-quality semantic knowledge base (SKB) for generative feature restoration. Finally, to simulate modern image transmission scenarios, we employ a diverse collection of high-resolution 2K images as the test set. The experimental results consistently demonstrate the superior performance of MOC-RVQ over conventional methods such as BPG or JPEG. Additionally, MOC-RVQ achieves comparable performance to an analog JSCC scheme, while needing only one-sixth of the channel bandwidth ratio (CBR) and being directly compatible with digital transmission systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_01272 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MOC-RVQ: Multilevel Codebook-Assisted Digital Generative Semantic Communication Zhou, Yingbin Sun, Yaping Chen, Guanying Xu, Xiaodong Chen, Hao Huang, Binhong Cui, Shuguang Zhang, Ping Computer Vision and Pattern Recognition Vector quantization-based image semantic communication systems have successfully boosted transmission efficiency, but face challenges with conflicting requirements between codebook design and digital constellation modulation. Traditional codebooks need wide index ranges, while modulation favors few discrete states. To address this, we propose a multilevel generative semantic communication system with a two-stage training framework. In the first stage, we train a high-quality codebook, using a multi-head octonary codebook (MOC) to compress the index range. In addition, a residual vector quantization (RVQ) mechanism is also integrated for effective multilevel communication. In the second stage, a noise reduction block (NRB) based on Swin Transformer is introduced, coupled with the multilevel codebook from the first stage, serving as a high-quality semantic knowledge base (SKB) for generative feature restoration. Finally, to simulate modern image transmission scenarios, we employ a diverse collection of high-resolution 2K images as the test set. The experimental results consistently demonstrate the superior performance of MOC-RVQ over conventional methods such as BPG or JPEG. Additionally, MOC-RVQ achieves comparable performance to an analog JSCC scheme, while needing only one-sixth of the channel bandwidth ratio (CBR) and being directly compatible with digital transmission systems. |
| title | MOC-RVQ: Multilevel Codebook-Assisted Digital Generative Semantic Communication |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.01272 |