This is the code of SLAMesh. This repository archive the state when the paper was submitted so that others can verificate our result (wait a while).

You are welcome to visit my personal repository and raise issues there so that I can receive immediate notifications. I may also update it more frequently but sometimes the result may slightly differ from the paper.

17/Aug/2023, Code released in the repo and also my personal repository.

03/10/2023, Preprint of our paper can be found on: paper. Code will be relased soon.

01/16/2023, The paper has been accepted for presentation on ICRA 2023,

This work designs a Simultaneously Localization And Meshing system (SLAMesh). It can build, registrate, and update the mesh maps in real-time with CPU resource. Mesh is a kind of 3-D dense model representations with low-memory consumption. It has the capability to model complex structures and has the feasibility for rendering. We bridge localization with meshing at the same time to benefit each other. The experiments show that our SLAMesh can run at around 40 Hz. The localization and meshing accuracy also outperforms the state-of-the-art methods.

On public dataset

On real-world

[email protected]