Dr.Joey

Could you elaborate what data were you running ESVO on? Have you obtained normally good Time Surfaces?

Then you may need to tune the depth perception range according to the dataset used. Please refer to [this issue](https://github.com/HKUST-Aerial-Robotics/ESVO/issues/15#issue-1034636262) for further detail. Hopefully it would help.

Hi @ghoshsuman, I remember you successfully build and run ESVO on Ubuntu 20.04 with ROS noetic. Could you disclose your cmake and gcc version here? Also, have you ever come...

Hi @nsgln, Not sure, but the follwing one may help. https://stackoverflow.com/questions/40611485/compiling-againt-another-version-of-eigen-using-cmake

Yes, you are right, I used the depth in the wrong way. Now the scale of the answer is right. But the estimated motion is still not coincide with the...

The first image is the estimation result and the second one is the ground truth. Transition in x,y,z direction are all different... Why

I think there may be some problems with my input. Because no matter how I change the way to load the input images, the registration result seems always good, but...

Hi, another problem is when I run the dvo, strange errors always happen, look below pease, ~/sophus_src/sophus/so3.cpp:45: Sophus::SO3::SO3(const Quaterniond&): Assertion 'unit_quaternion_.squaredNorm()>SAMLL_EPS' failed Aborted (core dumped) I don't know why this...

Thanks for your reply, Mr Christian. I just have download the dvo_core and successfully compile it. I have read your thesis and got your brilliant ideas. But I am not...

Hi Christian, There is a class called QMatrix in the Transform.h file. I cannot find where it was defined. Could you point it out for me. Thanks.