Our obtained trajectory from draw_odometry.py is quite different from your paper.

[NaoyaIshiguro]

issue

We ran python scripts/draw_odometry.py with the pre-trained model, kitti_raw_road.pth on the "KITTI Odometry" dataset.
But, the resulting trajectory is different from yours.
Both the evaluated values of RMSE, rotation error and the estimated values for the trajectory are different from the results in your paper(https://arxiv.org/pdf/2207.07895.pdf).

・The result in the paper
According to Table4
Average sequence translation RMSE (%): 4.57
Average sequence rotation error (deg/100m): 2.94
trajectry : Fig. 7

・Our result
Average sequence translation RMSE (%): 56.6012
Average sequence rotation error (deg/m): 0.4300

Runtime environment

azureml 1.44.0

Reproduction procedures

1. At draw_odometry.py:L28, KITTIOdomDataset argument "type" is now "static".
2. I created test_files_07.txt with 07/road_dense128/000000.png to 07/road_dense128/001100.png and placed it in JPerceiver/mono/datasets/splits/odometry/.
3. I set "~/<my_directory>/kitti_odometry_road.pth" in the path of model_path.
4. I set 7 in sequence_id.

our puopose

How to get the results of your paper ?