Neural Processes combine the strengths of neural networks and Gaussian processes to achieve both flexible learning and fast prediction in stochastic processes. However, a large class of problems comprises underlying temporal dependency structures in a sequence of stochastic processes that Neural Processes (NP) do not explicitly consider. In this paper, we propose Sequential Neural Processes (SNP) which incorporates a temporal state-transition model of stochastic processes and thus extends its modeling capabilities to dynamic stochastic processes. In applying SNP to dynamic 3D scene modeling, we introduce the Temporal Generative Query Networks. To our knowledge, this is the first 4D model that can deal with the temporal dynamics of 3D scenes. In experiments, we evaluate the proposed methods in dynamic (non-stationary) regression and 4D scene inference and rendering.
@article{arxiv.1906.10264,
title = {Sequential Neural Processes},
author = {Gautam Singh and Jaesik Yoon and Youngsung Son and Sungjin Ahn},
journal= {arXiv preprint arXiv:1906.10264},
year = {2019}
}
Comments
NeurIPS 2019 Spotlight. First two authors contributed equally