Cheng Feng comments

Results 10 comments of


                                            Cheng Feng

Question about the first optical flow estimator

@deqings Thanks for your reply! I have another question to ask. As everyone knows, PWC-Net has become the new baseline of many papers. I wonder if its pytorch version of...

Parameters for correlation

Hi, @marcbo12, This is my solution ``` from spatial_correlation_sampler import SpatialCorrelationSampler as Correlation self._corr = Correlation(kernel_size=1, patch_size=9, stride=1, padding=0, dilation_patch=1) def corr(self, input1, input2): out_corr = self._corr(input1, input2) # collate...

Data preparation

> > Thanks for your work! Using IMU is very instructive for solving the scale problem of monocular depth estimation. > > I think providing a detailed description of data...

Data preparation

Wow! Thanks for your quick response! @SenZHANG-GitHub Because most people who learn monocular depth estimation start from _MonoDepth_ with the synced data, re-downloading the unsynced data to run the _match_kitti_imu.py_...

Data preparation

I am looking forward to it! Best wishes to you.

Data preparation

Thanks for your work! I have retrained the network and it works good! I also find a little bug, please check the pull requests for detail.

some files seems damaged

> Hi! Thank you for having an interest in this work. > > I have checked the files. The files are well decompressed and the error doesn't occur. I think...

would you please share your paper

[https://arxiv.org/abs/1907.11628](url) @wzl2611 @Kwanss

would you please share your paper

@Kwanss Thank you for your work! Are you going to release the training code?

attention of the MCDB module as mentioned in the paper

me too