Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916453104484352 |
|---|---|
| author | Fan, Xiang Bhattad, Anand Krishna, Ranjay |
| author_facet | Fan, Xiang Bhattad, Anand Krishna, Ranjay |
| contents | We introduce Videoshop, a training-free video editing algorithm for localized semantic edits. Videoshop allows users to use any editing software, including Photoshop and generative inpainting, to modify the first frame; it automatically propagates those changes, with semantic, spatial, and temporally consistent motion, to the remaining frames. Unlike existing methods that enable edits only through imprecise textual instructions, Videoshop allows users to add or remove objects, semantically change objects, insert stock photos into videos, etc. with fine-grained control over locations and appearance. We achieve this through image-based video editing by inverting latents with noise extrapolation, from which we generate videos conditioned on the edited image. Videoshop produces higher quality edits against 6 baselines on 2 editing benchmarks using 10 evaluation metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14617 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion Fan, Xiang Bhattad, Anand Krishna, Ranjay Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning We introduce Videoshop, a training-free video editing algorithm for localized semantic edits. Videoshop allows users to use any editing software, including Photoshop and generative inpainting, to modify the first frame; it automatically propagates those changes, with semantic, spatial, and temporally consistent motion, to the remaining frames. Unlike existing methods that enable edits only through imprecise textual instructions, Videoshop allows users to add or remove objects, semantically change objects, insert stock photos into videos, etc. with fine-grained control over locations and appearance. We achieve this through image-based video editing by inverting latents with noise extrapolation, from which we generate videos conditioned on the edited image. Videoshop produces higher quality edits against 6 baselines on 2 editing benchmarks using 10 evaluation metrics. |
| title | Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2403.14617 |