Conf-Net: Toward High-Confidence Dense 3D Point-Cloud with Error-Map Prediction

This work proposes a method for depth completion of sparse LiDAR data using a convolutional neural network which can be used to generate semi-dense depth maps and 3D point-clouds with significantly lower root mean squared error (RMSE) over state-of-the-art methods.

Data and Resources

Cite this as

Hamid Hekmatian, Jingfu Jin, Samir Al-Stouhi (2024). Dataset: Conf-Net: Toward High-Confidence Dense 3D Point-Cloud with Error-Map Prediction. https://doi.org/10.57702/3xze7omr

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.1907.10148
Author Hamid Hekmatian
More Authors
Jingfu Jin
Samir Al-Stouhi
Homepage http://github.com/hekmak/Conf-net