Variational State-Space Models for Localisation and Dense 3D Mapping in
6 DoF
- URL: http://arxiv.org/abs/2006.10178v3
- Date: Mon, 15 Mar 2021 17:11:08 GMT
- Title: Variational State-Space Models for Localisation and Dense 3D Mapping in
6 DoF
- Authors: Atanas Mirchev, Baris Kayalibay, Patrick van der Smagt and Justin
Bayer
- Abstract summary: 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.
This results in an expressive predictive model of the world, often missing in current state-of-the-art visual SLAM solutions.
We evaluate our approach on realistic unmanned aerial vehicle flight data, nearing the performance of state-of-the-art visual-inertial odometry systems.
- Score: 17.698319441265223
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- IPoD: Implicit Field Learning with Point Diffusion for Generalizable 3D Object Reconstruction from Single RGB-D Images [50.4538089115248]
Generalizable 3D object reconstruction from single-view RGB-D images remains a challenging task.
We propose a novel approach, IPoD, which harmonizes implicit field learning with point diffusion.
Experiments conducted on the CO3D-v2 dataset affirm the superiority of IPoD, achieving 7.8% improvement in F-score and 28.6% in Chamfer distance over existing methods.
arXiv Detail & Related papers (2024-03-30T07:17:37Z) - SeisFusion: Constrained Diffusion Model with Input Guidance for 3D Seismic Data Interpolation and Reconstruction [26.02191880837226]
We propose a novel diffusion model reconstruction framework tailored for 3D seismic data.
We introduce a 3D neural network architecture into the diffusion model, successfully extending the 2D diffusion model to 3D space.
Our method exhibits superior reconstruction accuracy when applied to both field datasets and synthetic datasets.
arXiv Detail & Related papers (2024-03-18T05:10:13Z) - SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D
Object Pose Estimation [66.16525145765604]
We introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios.
Our approach formulates the 3D registration task as a denoising diffusion process, which progressively refines the pose of the source point cloud.
Experiments demonstrate that our diffusion registration framework presents outstanding pose estimation performance on the real-world TUD-L, LINEMOD, and Occluded-LINEMOD datasets.
arXiv Detail & Related papers (2023-10-26T12:47:26Z) - Learned Vertex Descent: A New Direction for 3D Human Model Fitting [64.04726230507258]
We propose a novel optimization-based paradigm for 3D human model fitting on images and scans.
Our approach is able to capture the underlying body of clothed people with very different body shapes, achieving a significant improvement compared to state-of-the-art.
LVD is also applicable to 3D model fitting of humans and hands, for which we show a significant improvement to the SOTA with a much simpler and faster method.
arXiv Detail & Related papers (2022-05-12T17:55:51Z) - Stereo Neural Vernier Caliper [57.187088191829886]
We propose a new object-centric framework for learning-based stereo 3D object detection.
We tackle a problem of how to predict a refined update given an initial 3D cuboid guess.
Our approach achieves state-of-the-art performance on the KITTI benchmark.
arXiv Detail & Related papers (2022-03-21T14:36:07Z) - A Model for Multi-View Residual Covariances based on Perspective
Deformation [88.21738020902411]
We derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups.
We validate our model with synthetic and real data and integrate it into photometric and feature-based Bundle Adjustment.
arXiv Detail & Related papers (2022-02-01T21:21:56Z) - Tracking and Planning with Spatial World Models [17.698319441265223]
We introduce a method for real-time navigation and tracking with differentiably rendered world models.
We achieve up to 92% navigation success rate at a frequency of 15 Hz using only image and depth observations.
arXiv Detail & Related papers (2022-01-25T14:16:46Z) - A Hybrid Sparse-Dense Monocular SLAM System for Autonomous Driving [0.5735035463793008]
We reconstruct a dense 3D model of the geometry of an outdoor environment using a single monocular camera attached to a moving vehicle.
Our system employs dense depth prediction with a hybrid mapping architecture combining state-of-the-art sparse features and dense fusion-based visual SLAM algorithms.
arXiv Detail & Related papers (2021-08-17T16:13:01Z) - Extracting Global Dynamics of Loss Landscape in Deep Learning Models [0.0]
We present a toolkit for the Dynamical Organization Of Deep Learning Loss Landscapes, or DOODL3.
DOODL3 formulates the training of neural networks as a dynamical system, analyzes the learning process, and presents an interpretable global view of trajectories in the loss landscape.
arXiv Detail & Related papers (2021-06-14T18:07:05Z) - Iterative Optimisation with an Innovation CNN for Pose Refinement [17.752556490937092]
In this work we propose an approach, namely an Innovation CNN, to object pose estimation refinement.
Our approach improves initial pose estimation progressively by applying the Innovation CNN iteratively in a gradient descent framework.
We evaluate our method on the popular LINEMOD and Occlusion LINEMOD datasets and obtain state-of-the-art performance on both datasets.
arXiv Detail & Related papers (2021-01-22T00:12:12Z) - Shape Prior Deformation for Categorical 6D Object Pose and Size
Estimation [62.618227434286]
We present a novel learning approach to recover the 6D poses and sizes of unseen object instances from an RGB-D image.
We propose a deep network to reconstruct the 3D object model by explicitly modeling the deformation from a pre-learned categorical shape prior.
arXiv Detail & Related papers (2020-07-16T16:45:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.