gt depth map fusion parameters

[Burningdust21]

Hi, thanks for a good work.
Could you provide your exact parameters for generating gt through fusing depth maps from IMC? I was fusing these scenes with parameters specified in paper "reprojection error below half a pixel and depth error below 1%", but the fusing result is not as good as the gt you provided. Thanks!

[fdarmon]

Hi,

The parameters specified in the paper are for the reconstructions with few images. For generating the ground truth, we use the same parameters except for the number of consistent views, we use 20.

Here are the exact colmap parameters:

StereoFusion.min_num_pixels = 20
StereoFusion.max_depth_error = 0.01
StereoFusion.max_reproj_error 

[Burningdust21]

Thanks, it helps.
But one more thing, how do you generate normal maps when fusing depth maps? Did you run a dense reconstruction before head?

[fdarmon]

I generate constant normal maps and simply ignore the normal filtering with

--StereoFusion.max_normal_error=180

[Burningdust21]

Great, thanks for the help.