arXiv (Cornell University) · 2020 · 263 citations · 34 references
Natural SciencesComputer SciencePhysicsAcousticsDifferential EquationsMachine LearningDeep LearningNeural ModelingNeural NetworksNeural RepresentationPartial Differential EquationsSignal ProcessingActivation FunctionsEikonal EquationInitializationNeural Representation LearningPoisson EquationPoisson's EquationSigned Distance FunctionsSiren Networks
Implicitly defined, continuous, differentiable signal representations parameterized by neural networks have emerged as a powerful paradigm, offering many possible benefits over conventional representations. However, current network architectures for such implicit neural representations are incapable of modeling signals with fine detail, and fail to represent a signal's spatial and temporal derivatives, despite the fact that these are essential to many physical signals defined implicitly as the solution to partial differential equations. We propose to leverage periodic activation functions for implicit neural representations and demonstrate that these networks, dubbed sinusoidal representation networks or Sirens, are ideally suited for representing complex natural signals and their derivatives. We analyze Siren activation statistics to propose a principled initialization scheme and demonstrate the representation of images, wavefields, video, sound, and their derivatives. Further, we show how Sirens can be leveraged to solve challenging boundary value problems, such as particular Eikonal equations (yielding signed distance functions), the Poisson equation, and the Helmholtz and wave equations. Lastly, we combine Sirens with hypernetworks to learn priors over the space of Siren functions.
34
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2015 · 18.8K citations
Maziar Raissi, Paris Perdikaris, George Em Karniadakis · Journal of Computational Physics · 2018 · 16.9K citations · Full text
Deep Learning Face Attributes in the Wild
Ziwei Liu, Ping Luo, Xiaogang Wang et al. · 2015 · 7.7K citations