Jinkuan Zhu

> As I know, we can calculate depth from disparity follow: depth = baseline * focal / disparity. > I'm using stereo_train_01.zip (4.4GB) to calculate depth map from disparity. I...

Hi, Many thanks for your reply! I also try to ask the writer of the paper published on CVPR. Yet I receive no feedback. Let's keep in contact!

> > > As I know, we can calculate depth from disparity follow: depth = baseline * focal / disparity. > > > I'm using stereo_train_01.zip (4.4GB) to calculate depth...

> Hi, > @Zhu-Jinkuan, > hello, I have a problem, I have not solved it. Can you discuss it together? Can you leave your contact information, thank you Hi, Do...

> The loss looks normal, maybe caused by the difference in batch-size. > This is my result in 128 batch-size. >  I guess you are right! When I create...

> > Hi, > > Thanks for your brilliant work for reproducing these methods. But when I follow your readme and train a 64bit DCMH on MIRFLICKR25K, the best results...

> I am also a little confused that I have downloaded the MAT file of MirflckR25K (red box in the picture). >  > Should I also need to download...

Hi, I use the pretrained kitti model to test a pciture in KITTI2015 and get the disparity map like this:  while the ground truth disparity map is as below...

Hi, How can I get the focal and the baseline of the KITTI datasets? Many thanks in advance for your reply. > With a known focal length and camera baseline...

> [#49 (comment)](https://github.com/mrharicot/monodepth/issues/49#issuecomment-330595397) Thanks for your reply! It really helps me a lot.