Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2408.11711 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909293068943360 |
|---|---|
| author | Ward, Rory Breslin, John G. Corcoran, Peter |
| author_facet | Ward, Rory Breslin, John G. Corcoran, Peter |
| contents | Adding color to black-and-white speaker videos automatically is a highly desirable technique. It is an artistic process that requires interactivity with humans for the best results. Many existing automatic video colorization systems provide little opportunity for the user to guide the colorization process. In this work, we introduce a novel automatic speaker video colorization system which provides controllability to the user while also maintaining high colorization quality relative to state-of-the-art techniques. We name this system ControlCol. ControlCol performs 3.5% better than the previous state-of-the-art DeOldify on the Grid and Lombard Grid datasets when PSNR, SSIM, FID and FVD are used as metrics. This result is also supported by our human evaluation, where in a head-to-head comparison, ControlCol is preferred 90% of the time to DeOldify. Example videos can be seen in the supplementary material. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_11711 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ControlCol: Controllability in Automatic Speaker Video Colorization Ward, Rory Breslin, John G. Corcoran, Peter Computer Vision and Pattern Recognition Adding color to black-and-white speaker videos automatically is a highly desirable technique. It is an artistic process that requires interactivity with humans for the best results. Many existing automatic video colorization systems provide little opportunity for the user to guide the colorization process. In this work, we introduce a novel automatic speaker video colorization system which provides controllability to the user while also maintaining high colorization quality relative to state-of-the-art techniques. We name this system ControlCol. ControlCol performs 3.5% better than the previous state-of-the-art DeOldify on the Grid and Lombard Grid datasets when PSNR, SSIM, FID and FVD are used as metrics. This result is also supported by our human evaluation, where in a head-to-head comparison, ControlCol is preferred 90% of the time to DeOldify. Example videos can be seen in the supplementary material. |
| title | ControlCol: Controllability in Automatic Speaker Video Colorization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.11711 |