Closed lorenzopapa5 closed 3 years ago
Hi,
This work uses official Train/Test split which is the same as the work you mentioned. But this project uses Raw depth maps instead of completed ones. You can refer to BTS repo for the data preparation for both NYU and KITTI datasets.
Checkout the minor correction
Dear authors,
Can you please confirm that the (NYU) Test and Train datasets are the same used in your old paper titled "High-Quality Monocular Depth Estimation via Transfer Learning"?
Thank you.