PromptMobile: Efficient Promptus for Low Bandwidth Mobile Video Streaming
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912376475877376 |
|---|---|
| author | Liu, Liming Wu, Jiangkai Wang, Haoyang Wang, Peiheng Guo, Zongming Zhang, Xinggong |
| author_facet | Liu, Liming Wu, Jiangkai Wang, Haoyang Wang, Peiheng Guo, Zongming Zhang, Xinggong |
| contents | Traditional video compression algorithms exhibit significant quality degradation at extremely low bitrates. Promptus emerges as a new paradigm for video streaming, substantially cutting down the bandwidth essential for video streaming. However, Promptus is computationally intensive and can not run in real-time on mobile devices. This paper presents PromptMobile, an efficient acceleration framework tailored for on-device Promptus. Specifically, we propose (1) a two-stage efficient generation framework to reduce computational cost by 8.1x, (2) a fine-grained inter-frame caching to reduce redundant computations by 16.6%, (3) system-level optimizations to further enhance efficiency. The evaluations demonstrate that compared with the original Promptus, PromptMobile achieves a 13.6x increase in image generation speed. Compared with other streaming methods, PromptMobile achives an average LPIPS improvement of 0.016 (compared with H.265), reducing 60% of severely distorted frames (compared to VQGAN). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16112 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PromptMobile: Efficient Promptus for Low Bandwidth Mobile Video Streaming Liu, Liming Wu, Jiangkai Wang, Haoyang Wang, Peiheng Guo, Zongming Zhang, Xinggong Networking and Internet Architecture Artificial Intelligence Multimedia Traditional video compression algorithms exhibit significant quality degradation at extremely low bitrates. Promptus emerges as a new paradigm for video streaming, substantially cutting down the bandwidth essential for video streaming. However, Promptus is computationally intensive and can not run in real-time on mobile devices. This paper presents PromptMobile, an efficient acceleration framework tailored for on-device Promptus. Specifically, we propose (1) a two-stage efficient generation framework to reduce computational cost by 8.1x, (2) a fine-grained inter-frame caching to reduce redundant computations by 16.6%, (3) system-level optimizations to further enhance efficiency. The evaluations demonstrate that compared with the original Promptus, PromptMobile achieves a 13.6x increase in image generation speed. Compared with other streaming methods, PromptMobile achives an average LPIPS improvement of 0.016 (compared with H.265), reducing 60% of severely distorted frames (compared to VQGAN). |
| title | PromptMobile: Efficient Promptus for Low Bandwidth Mobile Video Streaming |
| topic | Networking and Internet Architecture Artificial Intelligence Multimedia |
| url | https://arxiv.org/abs/2503.16112 |