CADepth-master icon indicating copy to clipboard operation
CADepth-master copied to clipboard

[3DV 2021] Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation

Results 5 CADepth-master issues
Sort by recently updated
recently updated
newest added

Hi, thanks for your remarkable work. I have some questions about Detail Emphasis Module. https://github.com/kamiLight/CADepth-master/blob/8251f12f21393aae3261c3765218063cea1cae30/networks/dem.py#L4-L19 I noticed that it contains 2 parts, the first is conv1, the second is global_path....

Hello, may I ask how Attention maps of SoTA methods and the corresponding error map are made? Could you please let me know?

Hello! Thanks for this great work! When training with mono_model, the output tensor size of the posenet is [B, 2, 1, 3] for both axisangle and translation. But when calculating...

I would like to Fine-tune this model or train again on my custom dataset on a CPU machine (Monocular images) Could you please help me with what all things I...

Hi and thanks for sharing your code online! When training my own models and comparing with the Monodepth2 framework, I noticed that CADepth-Net takes significantly less time to train with...