رسالة جامعية
Diverse Video Generation
العنوان: | Diverse Video Generation |
---|---|
المؤلفون: | Shrivastava, Gaurav |
المساهمون: | Shrivastava, Abhinav, Digital Repository at the University of Maryland, University of Maryland (College Park, Md.), Computer Science |
سنة النشر: | 2021 |
المجموعة: | University of Maryland: Digital Repository (DRUM) |
مصطلحات موضوعية: | Artificial intelligence, Computer science, Computer Vision, Gaussian Process, Video Generation |
الوصف: | Generating future frames given a few context (or past) frames is a challengingtask. It requires modeling the temporal coherence of videos and multi-modality in terms of diversity in the potential future states. Current variational approaches for video generation tend to marginalize over multi-modal future outcomes. Instead, in this thesis, we propose to explicitly model the multi-modality in the future outcomes and leverage it to sample diverse futures. Our approach, Diverse Video Generator, uses a Gaussian Process (GP) to learn priors on future states given the past and maintains a probability distribution over possible futures given a particular sample. In addition, we leverage the changes in this distribution overtime to control the sampling of diverse future states by estimating the end of on-going sequences. That is, we use the variance of GP over the output function space to trigger a change in an action sequence. We achieve state-of-the-art results on diverse future frame generation in terms of reconstruction quality and diversity of the generated sequences |
نوع الوثيقة: | thesis |
وصف الملف: | application/pdf |
اللغة: | English |
العلاقة: | https://doi.org/10.13016/mcxj-xwt3Test; http://hdl.handle.net/1903/27482Test |
DOI: | 10.13016/mcxj-xwt3 |
الإتاحة: | https://doi.org/10.13016/mcxj-xwt3Test http://hdl.handle.net/1903/27482Test |
رقم الانضمام: | edsbas.6F8A881D |
قاعدة البيانات: | BASE |
DOI: | 10.13016/mcxj-xwt3 |
---|