Official repository for CMax-SLAM: Event-based Rotational-Motion Bundle Adjustment and SLAM System using Contrast Maximization, IEEE T-RO 2024, by Shuang Guo and Guillermo Gallego.
If you use this work in your research, please consider citing:
@Article{Guo24tro, author = {Shuang Guo and Guillermo Gallego}, title = {{CMax}-{SLAM}: Event-based Rotational-Motion Bundle Adjustment and {SLAM} System using Contrast Maximization}, journal = {{IEEE} Transactions on Robotics}, year = 2024, volume = {40}, number = {}, pages = {2442--2461}, doi = {10.1109/TRO.2024.3378443} } @InProceedings{Gallego18cvpr, author = {Guillermo Gallego and Henri Rebecq and Davide Scaramuzza}, title = {A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation}, booktitle = {{IEEE} Conf. Comput. Vis. Pattern Recog. (CVPR)}, year = 2018, pages = {3867--3876}, doi = {10.1109/CVPR.2018.00407} }
Input:
- Events.
- Camera calibration.
Output:
- Rotational motion of the event camera.
- Local (front-end) and global (back-end) image of warped events (IWEs).
We also release the dataset that we made, see and download it from here. The instructions of running CMax-SLAM on the ECRot datasets can be found here.
This code leverages the following repository for computing the derivative of Lie Group B-splines: