VidPanos: Generative Panoramic Videos from Casual Panning Videos
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_ | 1866929562043023360 |
|---|---|
| author | Ma, Jingwei Lu, Erika Paiss, Roni Zada, Shiran Holynski, Aleksander Dekel, Tali Curless, Brian Rubinstein, Michael Cole, Forrester |
| author_facet | Ma, Jingwei Lu, Erika Paiss, Roni Zada, Shiran Holynski, Aleksander Dekel, Tali Curless, Brian Rubinstein, Michael Cole, Forrester |
| contents | Panoramic image stitching provides a unified, wide-angle view of a scene that extends beyond the camera's field of view. Stitching frames of a panning video into a panoramic photograph is a well-understood problem for stationary scenes, but when objects are moving, a still panorama cannot capture the scene. We present a method for synthesizing a panoramic video from a casually-captured panning video, as if the original video were captured with a wide-angle camera. We pose panorama synthesis as a space-time outpainting problem, where we aim to create a full panoramic video of the same length as the input video. Consistent completion of the space-time volume requires a powerful, realistic prior over video content and motion, for which we adapt generative video models. Existing generative models do not, however, immediately extend to panorama completion, as we show. We instead apply video generation as a component of our panorama synthesis system, and demonstrate how to exploit the strengths of the models while minimizing their limitations. Our system can create video panoramas for a range of in-the-wild scenes including people, vehicles, and flowing water, as well as stationary background features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_13832 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VidPanos: Generative Panoramic Videos from Casual Panning Videos Ma, Jingwei Lu, Erika Paiss, Roni Zada, Shiran Holynski, Aleksander Dekel, Tali Curless, Brian Rubinstein, Michael Cole, Forrester Computer Vision and Pattern Recognition Graphics I.3.3; I.4 Panoramic image stitching provides a unified, wide-angle view of a scene that extends beyond the camera's field of view. Stitching frames of a panning video into a panoramic photograph is a well-understood problem for stationary scenes, but when objects are moving, a still panorama cannot capture the scene. We present a method for synthesizing a panoramic video from a casually-captured panning video, as if the original video were captured with a wide-angle camera. We pose panorama synthesis as a space-time outpainting problem, where we aim to create a full panoramic video of the same length as the input video. Consistent completion of the space-time volume requires a powerful, realistic prior over video content and motion, for which we adapt generative video models. Existing generative models do not, however, immediately extend to panorama completion, as we show. We instead apply video generation as a component of our panorama synthesis system, and demonstrate how to exploit the strengths of the models while minimizing their limitations. Our system can create video panoramas for a range of in-the-wild scenes including people, vehicles, and flowing water, as well as stationary background features. |
| title | VidPanos: Generative Panoramic Videos from Casual Panning Videos |
| topic | Computer Vision and Pattern Recognition Graphics I.3.3; I.4 |
| url | https://arxiv.org/abs/2410.13832 |