Open sunnyHelen opened 3 years ago
Hi there,
There is a three-stage process to training. First, an unscaled depth network is required, which can be trained using our training procedure without using the scale recovery losses. Then, you can use this (unscaled) depth network to train the plane segmentation network. Following this, use the plane segmentation network (with the scale recovery losses) to train a new depth and egomotion network that will be metrically scaled.
Got it. Thanks a lot for your reply. BTW, do you have the test results of pose on Odometry sequences?
Hi. Thanks for sharing your great work. Should we train the Plane Segmentation Network before training the depth and ego-motion networks?