-
With other sensors, I got the trajectory of the camera at a real scale in a scene. The trajectory is not very accurate in a long time, but relatively accurate in a short time, and I want to use the ge…
-
thank you for your work~
-
Hi,
I am trying to use the groundtruth provided in the bag files to generate RMSE, but the ground truth seems to have a misalignment with the camera frame. Could you please share some details on how…
-
hello,I run the Submit_15_jobs_gromacs-ramd.sh,I have fininsh the project and get 15 trj,but in every files,there is nothing in out file,so I cant run the grep "GROMACS will be stopped after" TRJ*/*…
-
Hello! Thanks for the excellent work! I tried to reconstruct a street scene(I use Waymo dataset, and I just use left camera images ~200pics) using the 3d-gs and extract the mesh. But I find the result…
-
Hi there,
Thanks for your excellent code. I am running your code using my own Mujoco model to do peg hole insertion with algorithm_traj_opt only, (No neural net yet). It seems the first 15 iterati…
-
Hi @lahavlipson @zachteed!
Great work, thanks a lot for releasing such a neat implementation!
I wonder whether it is possible to obtain confidences in a way that is correlated with the camera po…
-
There seems to be an error in this method:
If there are no input trajectories (like in the parameter estimation problem I am playing around with right now) it tries to put a title on a non existing a…
-
Hello,
Why is the standard Umeyama algorithm not used for alignment and scaling of 5-frame trajectories when computing the ATE-5?
-
https://answers.ros.org/question/249874/tracked-robot-gazebo-ros/
https://pdfs.semanticscholar.org/9dbc/830fc9b8e85b8c84a2d993d40fa947e005ca.pdf
https://github.com/progtologist/gazebo-tracks