Closed zshn25 closed 4 years ago
Hi, In the original pydnet, in each decoder we get the disparity by slicing the last feature map. Here we obtain disparities with a convolutional layer.
Thank you. Could you tell me why these changes? Why replace transpose convolutions and why convolution layer for disparity at the end of decoder?
About transposed, also for this, while about disparity estimation, the number of parameters and time that slice allows to gain it’s quite limited, so I opted for these (minor) changes.
You have mentioned in the paper that transposed convolutions have been replaced by upsampling and convolution blocks. What else has been changed?