Stochastic Video Generation with a Learned Prior
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2018
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916157673439232 |
|---|---|
| author | Denton, Remi Fergus, Rob |
| author_facet | Denton, Remi Fergus, Rob |
| contents | Generating video frames that accurately predict future world states is challenging. Existing approaches either fail to capture the full distribution of outcomes, or yield blurry generations, or both. In this paper we introduce an unsupervised video generation model that learns a prior model of uncertainty in a given environment. Video frames are generated by drawing samples from this prior and combining them with a deterministic estimate of the future frame. The approach is simple and easily trained end-to-end on a variety of datasets. Sample generations are both varied and sharp, even many frames into the future, and compare favorably to those from existing approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1802_07687 |
| institution | arXiv |
| publishDate | 2018 |
| record_format | arxiv |
| spellingShingle | Stochastic Video Generation with a Learned Prior Denton, Remi Fergus, Rob Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.2.6; I.4 Generating video frames that accurately predict future world states is challenging. Existing approaches either fail to capture the full distribution of outcomes, or yield blurry generations, or both. In this paper we introduce an unsupervised video generation model that learns a prior model of uncertainty in a given environment. Video frames are generated by drawing samples from this prior and combining them with a deterministic estimate of the future frame. The approach is simple and easily trained end-to-end on a variety of datasets. Sample generations are both varied and sharp, even many frames into the future, and compare favorably to those from existing approaches. |
| title | Stochastic Video Generation with a Learned Prior |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.2.6; I.4 |
| url | https://arxiv.org/abs/1802.07687 |