ViP-DeepLab
ViP-DeepLab copied to clipboard
About sparsity of data
Thank you for your great work. I found that the depth map in your paper is denser than that in the dataset, did you interpolate the original depth map for visualization, or you also used interpolated depth map for training? And what kind of interpolation method did you use?
Thank you for your reply in advance, looking forward for your reply.
Hi @sconlyshootery
Thanks for the question. The paper shows denser labels only for visualization. During training, we used the sparse labels. Hope this is helpful.