Ask about the preprocessing of depth images
Opened this issue · 3 comments
bqm1111 commented
When training on NYUv2 dataset, did you use HHA encoding image as inputs or did you just use the colorization depth images? Furthermore, did you crop the white border of depth images?
ShaohuaDong2021 commented
We do not use the HHA, we only use the raw depth image and do not crop the white border of depth images.
bqm1111 commented
Thanks for your reply. I have another question regarding the preprocessing of image on SunRGBD dataset. This dataset has images with different sizes and ratios. How did you preprocess to train and evaluate this dataset fairly?
ShaohuaDong2021 commented
We followed Dformer, cropped the image to the same resolution.