Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF

Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt, Justin Bayer

Keywords: Generative models, Bayesian inference, Variational inference, SLAM, Deep learning

Abstract: We solve the problem of 6-DoF localisation and 3D dense reconstruction in spatial environments as approximate Bayesian inference in a deep state-space model. Our approach leverages both learning and domain knowledge from multiple-view geometry and rigid-body dynamics. This results in an expressive predictive model of the world, often missing in current state-of-the-art visual SLAM solutions. The combination of variational inference, neural networks and a differentiable raycaster ensures that our model is amenable to end-to-end gradient-based optimisation. We evaluate our approach on realistic unmanned aerial vehicle flight data, nearing the performance of state-of-the-art visual-inertial odometry systems. We demonstrate the applicability of the model to generative prediction and planning.

One-sentence Summary: We propose a variational state-space model with a latent map for 6-DoF localisation, 3D dense mapping and generative modelling for planning.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Data: [Blackbird](https://paperswithcode.com/dataset/blackbird)