Closed kwea123 closed 5 years ago
For stereo matching, it does not matter if the baselines are different because the outputs are disparity values (not dependent on the intrinsic parameters).
Another question, have you tried training on more than 100 images (e.g. on the whole training set) in the supervised setting? If so, does it perform better?
Yes, I will perform better. But our paper mainly focuses on the cases when there is no ground truth or very little ground truth data.
In your experiments, you use only the scene flow dataset as synthetic data. I wonder if the camera baselines (and other intrinsic parameters) are the same across the three different scenarios (flying things, driving, monkaa)? In my case, I want to train the proxy stereo net with scene flow and other additional data, does that degrade the network's performance due to different camera settings?