Densifying Sparse VIO: a Mesh-based approach using Structural Regularities

Abstract

The ideal vision system for an autonomous robot would not only provide the robot’s position and orientation (localization), but also an accurate and complete model of the scene (mapping). While localization information allows for controlling the robot, a map of the scene allows for collision-free navigation; combined, a robot can achieve full autonomy. Visual Inertial Odometry (VIO) algorithms have shown impressive localization results in recent years. Unfortunately, typical VIO algorithms use a point cloud to represent the scene, which is hardly usable for other tasks such as obstacle avoidance or path planning. In this work, we explore the possibility of generating a dense and consistent model of the scene by using a 3D mesh, while making use of structural regularities to improve both mesh and pose estimates. Our experimental results show that we can achieve a 26% more accurate pose estimates than state-of-the-art VIO algorithms when enforcing structural constraints, while also building a 3D mesh which provides a denser and more accurate map of the scene than a classical point cloud. We also show that our approach does not rely on assumptions about the scene and is general enough to work when structural regularities are not present. --> The ideal vision system for an autonomous robot would not only provide the robot’s position and orientation (localization), but also an accurate and complete model of the scene (mapping). While localization information allows for controlling the robot, a map of the scene allows for collision-free navigation; combined, a robot can achieve full autonomy. Visual Inertial Odometry (VIO) algorithms have shown impressive localization results in recent years. Unfortunately, typical VIO algorithms use a point cloud to represent the scene, which is hardly usable for other tasks such as obstacle avoidance or path planning. In this work, we explore the possibility of generating a dense and consistent model of the scene by using a 3D mesh, while making use of structural regularities to improve both mesh and pose estimates. Our experimental results show that we can achieve a 26\% more accurate pose estimates than state-of-the-art VIO algorithms when enforcing structural constraints, while also building a 3D mesh which provides a denser and more accurate map of the scene than a classical point cloud. We also show that our approach does not rely on assumptions about the scene and is general enough to work when structural regularities are not present.