When I am reproducing the results, I got v. wrong results, as shown below:
So when I checked plotting the depths and uncertainties saved in raw/disp and raw/uncert then they are like this (see image below, which is clearly wrong):
The thing is I am not getting proper raw pred_depths and uncertainties in raw directory, however my qualitative pred_depths and uncertainties are saved correctly in qual directory as shown below some examples:
So the main issue is when we are scaling the raw pred_depths and uncertainties before saving.
Could you please tell why we are multiplying by gt_depth's width in this line 270 of generate_maps.py: when you are saving the depths, why are you scaling it like this:
(I know depth = (baseline*focal_length)/disparity) but why by ratio, 256, 10 and gt_depth[i].shape[1] which is the width of the image.
And when saving uncertainties in line 279, why scaling like this: pred_uncerts[i]*(256*256-1)
So when using these saved maps in evaluate.py you are again scaling pred_depths like this before comparing with gt_depth: I can't understand line no. 167.
where you are dividing pred_disp like this: src = pred_disp / 256. / (0.58*gt_depth.shape[1]) * 10
Please help for this issue. @mattpoggi @FilippoAleotti @fabiotosi92
When I am reproducing the results, I got v. wrong results, as shown below:![terminal_output](https://user-images.githubusercontent.com/35197137/185294226-01c842cc-4a7c-46ee-bf8c-e05ccf89589d.jpg)
So when I checked plotting the depths and uncertainties saved in![notebook_output](https://user-images.githubusercontent.com/35197137/185290636-868952dd-ca12-476b-9e78-087a292f9070.png)
raw/disp
andraw/uncert
then they are like this (see image below, which is clearly wrong):The thing is I am not getting proper raw pred_depths and uncertainties in
![image](https://user-images.githubusercontent.com/35197137/185293227-261f1a13-d9eb-4580-b406-dd2dd77c2f64.png)
raw
directory, however my qualitative pred_depths and uncertainties are saved correctly inqual
directory as shown below some examples:So the main issue is when we are scaling the raw pred_depths and uncertainties before saving.
pred_disps[i]*(dataset.K[0][0]*gt_depths[i].shape[1])*256./ratio/10.
(I know depth = (baseline*focal_length)/disparity) but why by ratio, 256, 10 and gt_depth[i].shape[1] which is the width of the image.
And when saving uncertainties in line 279, why scaling like this:
pred_uncerts[i]*(256*256-1)
So when using these saved maps in evaluate.py you are again scaling pred_depths like this before comparing with gt_depth: I can't understand line no. 167. where you are dividing pred_disp like this:
src = pred_disp / 256. / (0.58*gt_depth.shape[1]) * 10
Please help for this issue. @mattpoggi @FilippoAleotti @fabiotosi92