search

lhoyer / improving_segmentation_with_selfsupervised_depth

[CVPR21] Implementation of our work "Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimation"
247 stars 30 forks source link

About paper presentations #20

Closed Renp1ngs closed 1 year ago

Renp1ngs commented 1 year ago

Dear hoyer:
I would very much like to know how those edges are drawn in the last column of Figure 5 of your conference paper. Hope to receive your reply. Best.

lhoyer commented 1 year ago

Dear @Renp1ngs,

For the visualization, we extract the edges from the mix mask, dilate them, and color the halves of the dilated edges according to the source image color code (orange/blue).

Best, Lukas