search

ShaohuaDong2021 / DPLNet

44 stars 0 forks source link

Ask about the preprocessing of depth images #8

Open bqm1111 opened 1 month ago

bqm1111 commented 1 month ago

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 1 month ago

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 1 month ago

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 4 weeks ago

We followed Dformer, cropped the image to the same resolution.