The error obtained when reproducing the TUM RGB-D data set is very large.

ivipsourcecode / dxslam

Other

415 stars 75 forks source link

The error obtained when reproducing the TUM RGB-D data set is very large. #32

Open Wingerllyyy opened 7 months ago

Wingerllyyy commented 7 months ago

  I downloaded the image (yerld/dxslam-built) in docker  and tested TUM RGB-D rgbd_dataset_fr3_walking_xyz data set. But the KeyFrameTrajectory.txt trajectory drawn using evo is very different from the ground truth, and the same is true for rgbd_dataset_freiburg1_xyz when tested. 
 What's  wrong with my  experiment?