# Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities

arXiv: https://arxiv.org/abs/1903.01067 · HTML: https://mlsanity.com/paper/1903.01067/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2019.

## Built on by (most cited first, 11 of 11)

- [Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs](https://mlsanity.com/paper/2101.06894/) (2021)
- [Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems](https://mlsanity.com/paper/2106.14386/) (2021)
- [Progressive Text-to-3D Generation for Automatic 3D Prototyping](https://mlsanity.com/paper/2309.14600/) (2023)
- [Comparison of modern open-source visual SLAM approaches](https://mlsanity.com/paper/2108.01654/) (2021)
- [E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs](https://mlsanity.com/paper/2207.10008/) (2022)
- [RP-VIO: Robust Plane-based Visual-Inertial Odometry for Dynamic Environments](https://mlsanity.com/paper/2103.10400/) (2021)
- [Unified Understanding of Environment, Task, and Human for Human-Robot Interaction in Real-World Environments](https://mlsanity.com/paper/2412.13726/) (2024)
- [Lidar-Monocular Surface Reconstruction Using Line Segments](https://mlsanity.com/paper/2104.02761/) (2021)
- [Smooth Mesh Estimation from Depth Data using Non-Smooth Convex Optimization](https://mlsanity.com/paper/2108.02957/) (2021)
- [TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images Using Joint 2D-3D Learning](https://mlsanity.com/paper/2204.10993/) (2022)
- [PRISM: Probabilistic Real-Time Inference in Spatial World Models](https://mlsanity.com/paper/2212.02988/) (2022)

## Abstract (arXiv)

Visual-Inertial Odometry (VIO) algorithms typically rely on a point cloud representation of the scene that does not model the topology of the environment. A 3D mesh instead offers a richer, yet lightweight, model. Nevertheless, building a 3D mesh out of the sparse and noisy 3D landmarks triangulated by a VIO algorithm often results in a mesh that does not fit the real scene. In order to regularize the mesh, previous approaches decouple state estimation from the 3D mesh regularization step, and either limit the 3D mesh to the current frame or let the mesh grow indefinitely. We propose instead to tightly couple mesh regularization and state estimation by detecting and enforcing structural regularities in a novel factor-graph formulation. We also propose to incrementally build the mesh by restricting its extent to the time-horizon of the VIO optimization; the resulting 3D mesh covers a larger portion of the scene than a per-frame approach while its memory usage and computational complexity remain bounded. We show that our approach successfully regularizes the mesh, while improving localization accuracy, when structural regularities are present, and remains operational in scenes without regularities.