Mu Hu

Thanks for your interest! We think that the camera intrinsic matrix should not be change. This is because when the image and the depth map are cropped, the corresponding coordinate...

Hi! There are actually two settings. Ours follows the one of Ma et al.(Sparse2Dense) to feed the full sized images into the models. And the other one is cropping the...

Thanks for your interest! In this project we don't directly take .bin files as inputs. However, I have a **naive** and **incomplete** **_python_** script for converting the .bin files to...

> hi, @JUGGHM I tried the code what you gave for converting .bin to .png format, but I have some doubt like, why still it need to read depth from...

> Yes Exactly, because currently I am having .npy format of depth map for 3D object detection. Now can i use this .npy file in your code to estimate dense...

> oh okay thank you very much for your quick replies. can we change hyper parameter values in Loss functions while training ? because it mentioned (0,0,0) I am just...

> oh okay thank you very much for your quick replies. can we change hyper parameter values in Loss functions while training ? because it mentioned (0,0,0) I am just...

> oh maybe i maybe misunderstood the logic over there, then what value you assigned as hyper parameter for your loss functions ? Thank you! `w_st1` and `w_st2`

> > oh okay thank you very much for your quick replies. can we change hyper parameter values in Loss functions while training ? because it mentioned (0,0,0) I am...

Thanks for your interest! It takes about 2~3 days to get ENet convergence at around epoch 20 in stage 1 and few hours in stage 2. But training in stage...