End-to-End Learning-based Video Streaming Enhancement Pipeline: A Generative AI Approach
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_ | 1866914203655208960 |
|---|---|
| author | Artioli, Emanuele Tashtarian, Farzad Timmerer, Christian |
| author_facet | Artioli, Emanuele Tashtarian, Farzad Timmerer, Christian |
| contents | The primary challenge of video streaming is to balance high video quality with smooth playback. Traditional codecs are well tuned for this trade-off, yet their inability to use context means they must encode the entire video data and transmit it to the client. This paper introduces ELVIS (End-to-end Learning-based VIdeo Streaming Enhancement Pipeline), an end-to-end architecture that combines server-side encoding optimizations with client-side generative in-painting to remove and reconstruct redundant video data. Its modular design allows ELVIS to integrate different codecs, inpainting models, and quality metrics, making it adaptable to future innovations. Our results show that current technologies achieve improvements of up to 11 VMAF points over baseline benchmarks, though challenges remain for real-time applications due to computational demands. ELVIS represents a foundational step toward incorporating generative AI into video streaming pipelines, enabling higher quality experiences without increased bandwidth requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14185 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | End-to-End Learning-based Video Streaming Enhancement Pipeline: A Generative AI Approach Artioli, Emanuele Tashtarian, Farzad Timmerer, Christian Multimedia Artificial Intelligence The primary challenge of video streaming is to balance high video quality with smooth playback. Traditional codecs are well tuned for this trade-off, yet their inability to use context means they must encode the entire video data and transmit it to the client. This paper introduces ELVIS (End-to-end Learning-based VIdeo Streaming Enhancement Pipeline), an end-to-end architecture that combines server-side encoding optimizations with client-side generative in-painting to remove and reconstruct redundant video data. Its modular design allows ELVIS to integrate different codecs, inpainting models, and quality metrics, making it adaptable to future innovations. Our results show that current technologies achieve improvements of up to 11 VMAF points over baseline benchmarks, though challenges remain for real-time applications due to computational demands. ELVIS represents a foundational step toward incorporating generative AI into video streaming pipelines, enabling higher quality experiences without increased bandwidth requirements. |
| title | End-to-End Learning-based Video Streaming Enhancement Pipeline: A Generative AI Approach |
| topic | Multimedia Artificial Intelligence |
| url | https://arxiv.org/abs/2512.14185 |