Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera.
Fangchang MaGuilherme Venturelli CavalheiroSertac KaramanPublished in: CoRR (2018)
Keyphrases
- monocular camera
- visual odometry
- feature tracking
- ground plane
- inertial sensors
- real time
- depth map
- multibody
- depth information
- depth images
- point cloud
- optical flow
- high resolution
- sparse representation
- multiple moving objects
- image sequences
- motion estimates
- urban areas
- position and orientation
- long range
- field of view