Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF
3. května 2021
Řečníci
Atanas Mirchev
Řečník · 0 sledujících
Baris Kayalibay
Řečník · 0 sledujících
Patrick van der Smagt
Řečník · 1 sledující
Justin Bayer
Řečník · 0 sledujících
O prezentaci
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.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…
O organizátorovi (ICLR 2021)
The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces
Zhlédnout později
Deep learning model compression using neural network design space exploration
Zhlédnout později
Data-Efficient Training of Autoencoders for Mildly Non-Linear Problems
Zhlédnout později
DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
Zhlédnout později
Adversarial Examples Make Stronger Poisons
Zhlédnout později
Liam Fowl, …