JiaxiongQ

ok,thanks

When estimating the ground-truth of surface normal from depth, we did the same operation to generate the color we want. So the surface normal from predicted depth should do this...

For KITTI, we fitted a plane for sparse depth points in a window. Please vist https://github.com/Cindy-xdZhang/surface-normal for details. On Wed, Jan 13, 2021 at 10:07 PM JennyGao00 wrote: > Can...

You can find these parameters in their official toolbox. On Sun, Jan 24, 2021 at 11:26 PM JennyGao00 wrote: > For KITTI, we fitted a plane for sparse depth points...

You need project your point cloud data to the color image camera coordinate and you'll get the sparse lidar depth, then you can use our test.py code to generate dense...

yes

Try to run this command: './tool'

Sorry, you can ask [email protected] for help.

No, the input only contains the color image and the sparse lidar depth.

gt_fold is for the ground-truth data. You should check your test environment firstly and you can pad the input dimension to make it can exactly divisible by 32.