Goto

Collaborating Authors

 Country



Appendix

Neural Information Processing Systems

ThepolytopeP(X,L) is in fact a "twisted sum" of a finite number of lattice polytopes fibering overP(F,L| F) .




ViSER: Video-SpecificSurfaceEmbeddingsfor Articulated3DShapeReconstruction

Neural Information Processing Systems

While there has been tremendous progress in reconstructing rigid scenes (via SfM and SLAM [7, 39, 43], or recent techniques based on neural rendering [28]), reconstructingdynamic scenes with articulated objects remains elusive.





f-DivergenceVariationalInference

Neural Information Processing Systems

For decades, the dominant paradigm for approximate Bayesian inferencep(z|x) = p(z,x)/p(x) has been Markov-Chain Monte-Carlo (MCMC) algorithms, which estimate the evidencep(x) = R p(z,x)dz via sampling. However, since sampling tends to be a slow and computationally intensive process, these sampling-based approximate inference methods fadewhendealing withthemodern probabilistic machine learning problems that usually involveverycomplexmodels, high-dimensional feature spaces andlargedatasets.


LightFieldNetworks: NeuralSceneRepresentations withSingle-EvaluationRendering

Neural Information Processing Systems

Inthe setting of simple scenes, we leverage meta-learning to learn a prior over LFNs that enables multi-view consistent light field reconstruction from as little as a singleimageobservation.