search

YoYo000 / BlendedMVS

BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
566 stars 40 forks source link

What does depth-wise pixel means？ #22

Open ss2lyf opened 2 years ago

ss2lyf commented 2 years ago

We note that in the Depth Map Validation, end point error (EPE), > 1 pixel error and > 3 pixel error are used to demonstrate the capacity of BlendedMVS dataset. However, what does depth-wise pixel means? Is it simply the difference values between the depth map and the ground truth depth map?

YoYo000 commented 2 years ago

The depth-wise pixel is measured by the depth interval. For example, the depth interval of the view is 2.5mm, the GT depth is 100mm, and the estimated depth is 110mm. Then the EPE is (110 - 100) / 2.5 = 4 pixels.

ss2lyf commented 2 years ago

For the cam.txt files in BlendedMVS like this:

extrinsic 0.865191 0.315296 -0.389914 0.105255 -0.453614 0.160702 -0.876589 0.236203 -0.213725 0.935288 0.282061 0.689507 0.0 0.0 0.0 1.0

intrinsic 1198.00875 0.0 384.45375 0.0 1198.00875 286.410375 0.0 0.0 1.0

1.21079 0.00412819 128.0 1.7392

Is the depth interval 0.00412819?

skill-diver commented 1 month ago

I am also wondering what does 1.21079 0.00412819 128.0 1.7392 in the last row mean?