-
Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data
We introduce Deep Variational Bayes Filters (DVBF), a new method for uns...
read it
-
Recency-weighted Markovian inference
We describe a Markov latent state space (MLSS) model, where the latent s...
read it
-
Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
We present a simple neural rendering architecture that helps variational...
read it
-
Factored Latent Analysis for far-field tracking data
This paper uses Factored Latent Analysis (FLA) to learn a factorized, se...
read it
-
Estimation and inference for area-wise spatial income distributions from grouped data
Estimating income distributions plays an important role in the measureme...
read it
-
Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
We solve the problem of 6-DoF localisation and 3D dense reconstruction i...
read it
-
Unsupervised Separation of Dynamics from Pixels
We present an approach to learn the dynamics of multiple objects from im...
read it
Variational Tracking and Prediction with Generative Disentangled State-Space Models
We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separately and including explicit position information in the latent state space, we perform tracking via amortized variational Bayesian inference of the respective latent positions. Inference is implemented in a modular neural framework tailored towards our disentangled latent space. Generative and inference model are jointly learned from observations only. Comparing to related prior work, we empirically show that our Markovian state-space assumption enables faithful and much improved long-term prediction well beyond the training horizon. Further, our inference model correctly decomposes frames into objects, even in the presence of occlusions. Tracking performance is increased significantly over prior art.
READ FULL TEXT
Comments
There are no comments yet.