search

aliyun / dro-sfm

MIT License
82 stars 12 forks source link

Bad odometry prediciton on kitti #3

Open TWJianNuo opened 3 years ago

TWJianNuo commented 3 years ago

Hi! Thanks for your great work and well-organized codebase!

I am trying to compare the odometry performance with yout method. I grab the public available supervised pretrained model from this repo. And I run the prediction on kitti odometry 00 sequence(2011_10_03/2011_10_03_drive_0027_sync). But the prediciton results is very strange. I wish to double-check is this coming from bug in my code. Basically, I add the prediciton named "poses" in "dro-sfm/dro_sfm/models/model_wrapper.py" from function "evaluate_depth()". Is this performance normal? I attach the odometry plot below Screenshot from 2021-05-22 01-05-10

manymuch commented 2 years ago

Did you calculate RTE on this or other odometry sequence?

manymuch commented 2 years ago

I used model trained from KITTI raw with self-supervised training, and test on Kitti Odometry sequence9: here is the result: image scale = 0.95 quaternion = [0.22 0.24 0.58 0.75] (x, y, z, w) translation = [-127.57 -43.16 127.21] (x, y, z) meters RTE = 53.56 % RRE = 30.07 deg/100m