Closed renyuanzhe closed 5 months ago
The shape is [batch_size, C, H, W]
The shape is [batch_size, C, H, W]
Doesn't it need img pairs in a sequence to train the model?
It uses adjacent frames to compute the loss, but the prediction is on a single frame.
so the gt of the input img is the adjacent frame of the input img ?
No. You can read the paper or the source code to get a quick idea of how self-supervised depth estimation works.
Is it something like [batch_size, sequence length, h ,w ,3]?