Chanoh Park

Sorry for the delay. Send me an email to my personal email. Let me see what I can do for you.

Hi, Thanks for your interest. I am working on the code on my private fork of this repo. It will be available soon in few weeks. I am struggling to...

> Hello, nice paper. Congratulation. > > Do you have a new ETA for the code release? Thanks! Now the paper's final version is submitted and I will finalize the...

> Sorry for the long wait. I recently resumed this project. But please note that what I can release is only some simulation and surfel visualization tools. The core implementation...

@HTLife I have look at the paper and your code again. It seems like the short batch trajectory structure is important as described in Figure4 of the original paper. SE3...

@HTLife I just found that read_R6TrajFile is reading relative pose as 1x6 vector whereas the saved relative pose file is actually written in quaternion format. Is sampleGT_relative.py right code to...

@HTLife Regarding the input of the IMU RNN, I guess it should include every IMU data between two image frames but it seems like your code is loading only 5...

@HTLife Regarding IMU data, camera is 20Hz and IMU is 200Hz. The training dataset has 2280 images, 22801 imu measurements which mean there should be 10 imu measurements between two...

IMU -- @HTLife Thanks for the explanation. VICON -- I just found that the vicon time stamp and IMU stamp is not actually recorded in the same system. (IMU and...

@HTLife It seems like they used gravity removed acceleration. If the acceleration is not removed eq 10 and 13 is totally wrong. This is important but not mentioned in any...