sconly

Hi, I am new to the data processing of IMU, I want to know how to calculate relative pose between two adjacent frames from kitti

Python.h: No such file or directory

2

building went wrong, as pangolin/external/pybind11/include/pybind11/detail/common.h:111:20: fatal error: Python.h: No such file or directory

Any idea to release a pytorch version？

3

Thank you for your great work and codes, this work is amazing. Tensorflow is difficult for using and developing, any idea to release a pytorch version?

https://github.com/princeton-vl/DeepV2D/blob/eb362f2f25338faf5adbd7818f1517018bfbc4b5/deepv2d/trainer.py#L203 Thanks for your great work, please help me figure out why here self.total_loss is set to depth_loss.

Thank you for your great work! I want to know how following derivation is achieved:  Could you please refer me some material from which I can...

Thank you for your great work, I want to know do you have any idea to release the pytorch version of deepv2d with lietorch?

How to do initialization for multiprocessing?

5

For a program A where multiprocessing is conducted to run program B, it seems that I could only put ti.init() in B rather A, causing wasting a lot of time...

About sparsity of data

1

Thank you for your great work. I found that the depth map in your paper is denser than that in the dataset, did you interpolate the original depth map for...

Does every test sample need a corresponding sparse depth map to improve testing accuracy?

1

It seems that every z is generated from a particular test sample x, we need ground truth sparse depth map D_s to update z for each x. Does it mean...