# RP-VIO: Robust Plane-based Visual-Inertial Odometry for Dynamic Environments

arXiv: https://arxiv.org/abs/2103.10400 · HTML: https://mlsanity.com/paper/2103.10400/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 60 references that are in the map.
- First posted on arXiv 18 Mar 2021.

## Builds on (most cited first, 18 of 18)

- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping](https://mlsanity.com/paper/1910.02490/) (2019)
- [On-Manifold Preintegration for Real-Time Visual-Inertial Odometry](https://mlsanity.com/paper/1512.02363/) (2015)
- [DS-SLAM: A Semantic Visual SLAM towards Dynamic Environments](https://mlsanity.com/paper/1809.08379/) (2018)
- [DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM](https://mlsanity.com/paper/2010.07820/) (2020)
- [Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM](https://mlsanity.com/paper/1911.05603/) (2019)
- [Visual-Inertial Monocular SLAM with Map Reuse](https://mlsanity.com/paper/1610.05949/) (2016)
- [Visual-Inertial Navigation: A Concise Review](https://mlsanity.com/paper/1906.02650/) (2019)
- [SelfVIO: Self-Supervised Deep Monocular Visual-Inertial Odometry and Depth Estimation](https://mlsanity.com/paper/1911.09968/) (2019)
- [ADVIO: An authentic dataset for visual-inertial odometry](https://mlsanity.com/paper/1807.09828/) (2018)
- [FlightGoggles: A Modular Framework for Photorealistic Camera, Exteroceptive Sensor, and Dynamics Simulation](https://mlsanity.com/paper/1905.11377/) (2019)
- [VIODE: A Simulated Dataset to Address the Challenges of Visual-Inertial Odometry in Dynamic Environments](https://mlsanity.com/paper/2102.05965/) (2021)
- [Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities](https://mlsanity.com/paper/1903.01067/) (2019)
- [OrcVIO: Object residual constrained Visual-Inertial Odometry](https://mlsanity.com/paper/2007.15107/) (2020)
- [Co-Planar Parametrization for Stereo-SLAM and Visual-Inertial Odometry](https://mlsanity.com/paper/2009.12662/) (2020)
- [RaD-VIO: Rangefinder-aided Downward Visual-Inertial Odometry](https://mlsanity.com/paper/1810.08704/) (2018)

## Built on by (most cited first, 3 of 3)

- [RD-VIO: Robust Visual-Inertial Odometry for Mobile Augmented Reality in Dynamic Environments](https://mlsanity.com/paper/2310.15072/) (2023)
- [Tightly-Coupled LiDAR-Visual SLAM Based on Geometric Features for Mobile Agents](https://mlsanity.com/paper/2307.07763/) (2023)
- [STAG-VIO: Stabilized Prompt-to-Geometry Interface for Robust Dynamic Visual--Inertial Odometry](https://mlsanity.com/paper/2411.19289/) (2024)

## Abstract (arXiv)

Modern visual-inertial navigation systems (VINS) are faced with a critical challenge in real-world deployment: they need to operate reliably and robustly in highly dynamic environments. Current best solutions merely filter dynamic objects as outliers based on the semantics of the object category. Such an approach does not scale as it requires semantic classifiers to encompass all possibly-moving object classes; this is hard to define, let alone deploy. On the other hand, many real-world environments exhibit strong structural regularities in the form of planes such as walls and ground surfaces, which are also crucially static. We present RP-VIO, a monocular visual-inertial odometry system that leverages the simple geometry of these planes for improved robustness and accuracy in challenging dynamic environments. Since existing datasets have a limited number of dynamic elements, we also present a highly-dynamic, photorealistic synthetic dataset for a more effective evaluation of the capabilities of modern VINS systems. We evaluate our approach on this dataset, and three diverse sequences from standard datasets including two real-world dynamic sequences and show a significant improvement in robustness and accuracy over a state-of-the-art monocular visual-inertial odometry system. We also show in simulation an improvement over a simple dynamic-features masking approach. Our code and dataset are publicly available.