search

Beniko95J / MLF-VO

Multi-Layer Fusion Visual Odometry
GNU General Public License v3.0
20 stars 3 forks source link

Leveraging velodyne laser data #7

Open bob292 opened 1 year ago

bob292 commented 1 year ago

Dear @Beniko95J ,

Thanks for your work!

Since one of the main contributions of MLF-VO is the multi-layer fusion of rgb and depth information, and as KITTI dataset also provides Lidar point cloud, I wonder if I could create input depth images by performing depth completion [https://www.cvlibs.net/datasets/kitti/eval_depth.php?benchmark=depth_completion] on current image and Lidar scan.

Theoretically, MLF-VO is able to obtain good results with these ground-truth depths. But I don't quite understand what exactly is this cur_disp (https://github.com/Beniko95J/MLF-VO/blob/659bc820843e08faaa29a6eff5e69f01513cf7ff/run_odometry.py#L117) , is it the disparity, the inverse depth or the depth. Could you please specify the mean and also the unity of it? Thanks in advance!

Yours, X. Shen

Beniko95J commented 1 year ago

Hi, thank you for the interests.

The prev_disp and cur_disp are the sigmoid outputs from the depth network (range from 0 - 1, you can treat this approximately as inverse_depth), and can be further converted into depth through this function. Hope this can be helpful.