Rethinking Image Compression on the Web with Generative AI
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_ | 1866929410524839936 |
|---|---|
| author | Hassan, Shayan Ali Humair, Danish Qazi, Ihsan Ayyub Qazi, Zafar Ayyub |
| author_facet | Hassan, Shayan Ali Humair, Danish Qazi, Ihsan Ayyub Qazi, Zafar Ayyub |
| contents | The rapid growth of the Internet, driven by social media, web browsing, and video streaming, has made images central to the Web experience, resulting in significant data transfer and increased webpage sizes. Traditional image compression methods, while reducing bandwidth, often degrade image quality. This paper explores a novel approach using generative AI to reconstruct images at the edge or client-side. We develop a framework that leverages text prompts and provides additional conditioning inputs like Canny edges and color palettes to a text-to-image model, achieving up to 99.8% bandwidth savings in the best cases and 92.6% on average, while maintaining high perceptual similarity. Empirical analysis and a user study show that our method preserves image meaning and structure more effectively than traditional compression methods, offering a promising solution for reducing bandwidth usage and improving Internet affordability with minimal degradation in image quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04542 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rethinking Image Compression on the Web with Generative AI Hassan, Shayan Ali Humair, Danish Qazi, Ihsan Ayyub Qazi, Zafar Ayyub Networking and Internet Architecture Computer Vision and Pattern Recognition Machine Learning Image and Video Processing The rapid growth of the Internet, driven by social media, web browsing, and video streaming, has made images central to the Web experience, resulting in significant data transfer and increased webpage sizes. Traditional image compression methods, while reducing bandwidth, often degrade image quality. This paper explores a novel approach using generative AI to reconstruct images at the edge or client-side. We develop a framework that leverages text prompts and provides additional conditioning inputs like Canny edges and color palettes to a text-to-image model, achieving up to 99.8% bandwidth savings in the best cases and 92.6% on average, while maintaining high perceptual similarity. Empirical analysis and a user study show that our method preserves image meaning and structure more effectively than traditional compression methods, offering a promising solution for reducing bandwidth usage and improving Internet affordability with minimal degradation in image quality. |
| title | Rethinking Image Compression on the Web with Generative AI |
| topic | Networking and Internet Architecture Computer Vision and Pattern Recognition Machine Learning Image and Video Processing |
| url | https://arxiv.org/abs/2407.04542 |