cleinc / bts

From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Why you use mask = depth_gt > 0.1 ?

mathjihun opened this issue · comments

I'm curious as to why the code specifically uses mask = depth_gt > 0.1 for the nyu_depth dataset. Is there a specific reason for this threshold? Also, would using a lower threshold such as mask = depth_gt > 0.001 not be effective?