- Notifications
You must be signed in to change notification settings - Fork11
Symbolic Continuous-Time Gaussian Belief Propagation Framework with Ceres Interoperability
License
VIS4ROB-lab/hyperion
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
A high-performance Continuous-Time Gaussian Belief Propagation (CT-GBP) framework with fully automated symbolic factor generation and seamless Ceres interoperability targeting distributed SLAM operations!
Report Issues or Request Features
Hyperion is a novel, modular, distributed, high-performance optimization framework targeting both discrete- andcontinuous-time SLAM (Simultaneous Localization and Mapping) applications. It stands out by offering thefirst open-source C++ implementation of a Gaussian-Belief-Propagation-based Non-Linear Least Squares solver, which,in turn, offers native support for decentralized, stochastic inference on factor graphs. In addition, Hyperion alsoextendsSymForce to automate the generation of high-performanceimplementations for spline-related residuals from symbolic, high-level expressions. This results in the fastest,Ceres-interoperable B- and Z-Spline implementations, achieving speedups of up to 110x overprevious state-of-the-art methods. Links toPaper,Poster, andVideo.
Hyperion was presented at theEuropean Conference on Computer Vision 2024 (ECCV 2024).Until the final version of record becomes available, please cite its archived version as follows:
@inproceedings{Hug:etal:ECCV2024, title={{Hyperion -- A fast, versatile symbolic Gaussian Belief Propagation framework for Continuous-Time SLAM}}, author={David Hug and Ignacio Alzugaray and Margarita Chli}, booktitle={Computer Vision -- ECCV 2024}, year={2024}, publisher={Springer Nature Switzerland}, address={Cham}, pages={215--231}, isbn={978-3-031-73404-5}, doi={10.1007/978-3-031-73404-5_13}}Additional documentation for installing and using Hyperion will be available soon. The framework comprises two mainmodules: a Python-based symbolic code generation module and an optimization module for performing inference on generalfactor graphs. Currently, three executables are provided: one for demonstrating how toset up a minimization problem in Hyperion, and two others for runningtests andbenchmarks. Hyperion's API closely mirrors that ofCeres, offering familiarity for users of that library. Additionally, asample benchmark run is included for reference, detailing the metrics reportedin the paper.
