Latent Neural Differential Equations for Video Generation

Cade Gordon, Natalie Parde
NeurIPS 2020 Workshop on Pre-registration in Machine Learning, PMLR 148:73-86, 2021.

Abstract

Generative Adversarial Networks have recently shown promise for video generation, building off of the success of image generation while also addressing a new challenge: time. Although time was analyzed in some early work, the literature has not adequately grown with temporal modeling developments. We study the effects of Neural Differential Equations to model the temporal dynamics of video generation. The paradigm of Neural Differential Equations presents many theoretical strengths including the first continuous representation of time within video generation. In order to address the effects of Neural Differential Equations, we investigate how changes in temporal models affect generated video quality. Our results give support to the usage of Neural Differential Equations as a simple replacement for older temporal generators. While keeping run times similar and decreasing parameter count, we produce a new state-of-the-art model in 64$\times$64 pixel unconditional video generation, with an Inception Score of 15.20.

Cite this Paper


BibTeX
@InProceedings{pmlr-v148-gordon21a, title = {Latent Neural Differential Equations for Video Generation}, author = {Gordon, Cade and Parde, Natalie}, booktitle = {NeurIPS 2020 Workshop on Pre-registration in Machine Learning}, pages = {73--86}, year = {2021}, editor = {Bertinetto, Luca and Henriques, João F. and Albanie, Samuel and Paganini, Michela and Varol, Gül}, volume = {148}, series = {Proceedings of Machine Learning Research}, month = {11 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v148/gordon21a/gordon21a.pdf}, url = {http://proceedings.mlr.press/v148/gordon21a.html}, abstract = {Generative Adversarial Networks have recently shown promise for video generation, building off of the success of image generation while also addressing a new challenge: time. Although time was analyzed in some early work, the literature has not adequately grown with temporal modeling developments. We study the effects of Neural Differential Equations to model the temporal dynamics of video generation. The paradigm of Neural Differential Equations presents many theoretical strengths including the first continuous representation of time within video generation. In order to address the effects of Neural Differential Equations, we investigate how changes in temporal models affect generated video quality. Our results give support to the usage of Neural Differential Equations as a simple replacement for older temporal generators. While keeping run times similar and decreasing parameter count, we produce a new state-of-the-art model in 64$\times$64 pixel unconditional video generation, with an Inception Score of 15.20.} }
Endnote
%0 Conference Paper %T Latent Neural Differential Equations for Video Generation %A Cade Gordon %A Natalie Parde %B NeurIPS 2020 Workshop on Pre-registration in Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Luca Bertinetto %E João F. Henriques %E Samuel Albanie %E Michela Paganini %E Gül Varol %F pmlr-v148-gordon21a %I PMLR %P 73--86 %U http://proceedings.mlr.press/v148/gordon21a.html %V 148 %X Generative Adversarial Networks have recently shown promise for video generation, building off of the success of image generation while also addressing a new challenge: time. Although time was analyzed in some early work, the literature has not adequately grown with temporal modeling developments. We study the effects of Neural Differential Equations to model the temporal dynamics of video generation. The paradigm of Neural Differential Equations presents many theoretical strengths including the first continuous representation of time within video generation. In order to address the effects of Neural Differential Equations, we investigate how changes in temporal models affect generated video quality. Our results give support to the usage of Neural Differential Equations as a simple replacement for older temporal generators. While keeping run times similar and decreasing parameter count, we produce a new state-of-the-art model in 64$\times$64 pixel unconditional video generation, with an Inception Score of 15.20.
APA
Gordon, C. & Parde, N.. (2021). Latent Neural Differential Equations for Video Generation. NeurIPS 2020 Workshop on Pre-registration in Machine Learning, in Proceedings of Machine Learning Research 148:73-86 Available from http://proceedings.mlr.press/v148/gordon21a.html.

Related Material