DepthFromDefocusWithLearnedOptics icon indicating copy to clipboard operation
DepthFromDefocusWithLearnedOptics copied to clipboard

ICCP2021: Depth from Defocus with Learned Optics for Imaging and Occlusion-aware Depth Estimation

Results 3 DepthFromDefocusWithLearnedOptics issues
Sort by recently updated
recently updated
newest added

I notice that stretch_depth function in ./datasets/sceneflow.py is not used, so the training depth maps are rescaled to [0, 1] instead of [1, 5] as mentioned in the paper. I...

Hi there, Thanks for your valuable work for the community. Currently, I am attempting to understand the forward function of camera, but I have trouble to understand what you are...

Hi, Thanks for a very interesting work, I want to train the code on my own dataset but I can't find a suitable torch version to support the code without...