Estimating-Depth-from-RGB-and-Sparse-Sensing
Estimating-Depth-from-RGB-and-Sparse-Sensing copied to clipboard
lakshjaisinghani
A a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels.
Looking through the code, I found a problem again. In, train.py 153~156 lines. ``` model = D3().float() model = model.to(device) Loss_fun = nn.MSELoss() optimizer = optim.Adam(net.parameters(), lr = learning_rate) ```...
Looking through the code, I found a problem. When you train, you need to get the image and raw depth as sparse_input, and get the depth completed by depth completion...
Metadata
Owner
Metadata
A a deep model that can accurately produce dense depth maps given an RGB image with known depth at a very sparse set of pixels.