search

yosungho / LineTR

Line as a Visual Sentence: Context-aware Line Descriptor for Visual Localization (Line Transformer)
Other
233 stars 35 forks source link

About the selection of points #20

Open yiyihao2000 opened 6 months ago

yiyihao2000 commented 6 months ago

Hello, you have done a great job and would like to ask you a few questions. Does the effect of image scaling be taken into account when calculating the number of points on a line segment at 8 intervals? And does scaling the image to a specified size affect the number of points selected on the segment?

yosungho commented 6 months ago

The model was trained with 640x480 images with 8-pixel intervals. The pre-trained weight works best with the same setup, so it would prefer to resize the input image to 640x480.