Open hillaric opened 2 years ago
Yes, different maximum disparity demands of your data could be the reason for bad performance. Did you fine-tune the model on your data? This is often necessary for good performance, especially on data that does not closely resemble the traffic scenes of KITTI or DrivingStereo.
Does the maxdisp value has a influence on the result of inference time or the performance? Besides, the result does not work well on my own dataset, I guess it is the problem of maxdisp value.