/dvs_mcemvs

Official implementation of AISY 2022 paper MC-EMVS: "Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion"

Primary LanguageC++OtherNOASSERTION

Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion

Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion

This is the code for the journal paper Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion, by Suman Ghosh and Guillermo Gallego, published at Advanced Intelligent Systems.

The PDF of the paper is available. If you use this work in your research, please cite it as follows:

@article{Ghosh22aisy,
  author = {Ghosh, Suman and Gallego, Guillermo},  
  title = {Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion},
  journal = {Advanced Intelligent Systems},
  year = {2022},
  doi = {10.1002/aisy.202200221}
}

Data Processing Pipeline

pipeline

Input

  • Events from multiple cameras
  • Pose of camera rig
  • Camera calibration (instrinsic, extrinsic, hand-eye) parameters

Output

  • Depth map
  • Confidence map
  • Point cloud
  • Intermediate ray density maps / Disparity Space Images (DSI)

Code

License

The license is available here.

Additional Resources on Event-based Vision