Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912873163259904 |
|---|---|
| author | Gong, Tianyi Cao, Zijian Zhang, Zixing Wu, Jiangkai Zhang, Xinggong Cui, Shuguang Wang, Fangxin |
| author_facet | Gong, Tianyi Cao, Zijian Zhang, Zixing Wu, Jiangkai Zhang, Xinggong Cui, Shuguang Wang, Fangxin |
| contents | Video streaming is a fundamental Internet service, while the quality still cannot be guaranteed especially in poor network conditions such as bandwidth-constrained and remote areas. Existing works mainly work towards two directions: traditional pixel-codec streaming nearly approaches its limit and is hard to step further in compression; the emerging neural-enhanced or generative streaming usually fall short in latency and visual fidelity, hindering their practical deployment. Inspired by the recent success of vision foundation model (VFM), we strive to harness the powerful video understanding and processing capacities of VFM to achieve generalization, high fidelity and loss resilience for real-time video streaming with even higher compression rate. We present the first revolutionized paradigm that enables VFM-based end-to-end generative video streaming towards this goal. Specifically, Morphe employs joint training of visual tokenizers and variable-resolution spatiotemporal optimization under simulated network constraints. Additionally, a robust streaming system is constructed that leverages intelligent packet dropping to resist real-world network perturbations. Extensive evaluation demonstrates that Morphe achieves comparable visual quality while saving 62.5\% bandwidth compared to H.265, and accomplishes real-time, loss-resilient video delivery in challenging network environments, representing a milestone in VFM-enabled multimedia streaming solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03529 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model Gong, Tianyi Cao, Zijian Zhang, Zixing Wu, Jiangkai Zhang, Xinggong Cui, Shuguang Wang, Fangxin Networking and Internet Architecture Artificial Intelligence Multimedia Video streaming is a fundamental Internet service, while the quality still cannot be guaranteed especially in poor network conditions such as bandwidth-constrained and remote areas. Existing works mainly work towards two directions: traditional pixel-codec streaming nearly approaches its limit and is hard to step further in compression; the emerging neural-enhanced or generative streaming usually fall short in latency and visual fidelity, hindering their practical deployment. Inspired by the recent success of vision foundation model (VFM), we strive to harness the powerful video understanding and processing capacities of VFM to achieve generalization, high fidelity and loss resilience for real-time video streaming with even higher compression rate. We present the first revolutionized paradigm that enables VFM-based end-to-end generative video streaming towards this goal. Specifically, Morphe employs joint training of visual tokenizers and variable-resolution spatiotemporal optimization under simulated network constraints. Additionally, a robust streaming system is constructed that leverages intelligent packet dropping to resist real-world network perturbations. Extensive evaluation demonstrates that Morphe achieves comparable visual quality while saving 62.5\% bandwidth compared to H.265, and accomplishes real-time, loss-resilient video delivery in challenging network environments, representing a milestone in VFM-enabled multimedia streaming solutions. |
| title | Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model |
| topic | Networking and Internet Architecture Artificial Intelligence Multimedia |
| url | https://arxiv.org/abs/2602.03529 |