search

fangchangma / self-supervised-depth-completion

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"
MIT License
621 stars 135 forks source link

About reduce scan lines of LiDAR depth #6

Open JiaxiongQ opened 5 years ago

JiaxiongQ commented 5 years ago

How do you reduce the scan lines of the LiDAR depth(64-line to 32-line...)? Could you share your code or your idea about this?

fangchangma commented 5 years ago

The downsampling process is non-trivial. We kept a subset of the laser scans, which were then projected onto the image plane. However, since some lidar measurements were missing in the raw file (due to being out of sensor range), it is a bit tricky to separate the scans in a clean way.

We might release the downsampled dataset / the code later

JiaxiongQ commented 5 years ago

ok,thanks

longyangqi commented 4 years ago

The downsampling process is non-trivial. We kept a subset of the laser scans, which were then projected onto the image plane. However, since some lidar measurements were missing in the raw file (due to being out of sensor range), it is a bit tricky to separate the scans in a clean way.

We might release the downsampled dataset / the code later

Is the downsampled dataset / the code available now? Thanks!

godspeed1989 commented 4 years ago

Expecting the release of downsampling code. Thanks!