Closed gyes00205 closed 1 year ago
Excellent catch! I'll look into this and push a fix along with bug fix for intrinsics.
Thanks!
Hello,
This is now fixed. We're not using OpenCV and Kornia style normalization for projection. Thanks a lot for pointing it out!
Hi authors, Thanks for your amazing works. I have a question about mask in meta data. In line 82 of
geometry_utils.py
, you usetorch.maximum
to make depth value greater or equal toeps
https://github.com/nianticlabs/simplerecon/blob/7de5b451e340f9a11c7fd67bd0c42204d0b009a9/utils/geometry_utils.py#L62-L85And in line 622-623 of
cost_volume.py
, you letmask_b = depths > 0
. But depth value of each pixel is greater than zero because oftorch.maximum()
in previous step, so themask_b
will all beTrue
.https://github.com/nianticlabs/simplerecon/blob/7de5b451e340f9a11c7fd67bd0c42204d0b009a9/modules/cost_volume.py#L618-L623
Then you concatenate the mask of each source image into meta data, but these mask are all
True
in every pixel of each source image. Aren't these mask value of meta data redundant? Or is there some wrong of mask computation?