search

ruili3 / dynamic-multiframe-depth

[CVPR 2023] Multi-frame depth estimation in dynamic scenes. -- Li, Rui, et al. "Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes".
MIT License
125 stars 7 forks source link

The problem of calculating dynamic regional indicators #11

Closed WangXuCh closed 8 months ago

WangXuCh commented 1 year ago

Hello, may I ask how to calculate indicators separately for dynamic areas?Looking forward to your reply!

ruili3 commented 1 year ago

thanks for your interest

We average depth errors over the intersection of dynamic masks and valid depth masks for dynamic evaluation. You can refer to the evaluation code and metric code for details :)

WangXuCh commented 1 year ago

thanks for your interest

We average depth errors over the intersection of dynamic masks and valid depth masks for dynamic evaluation. You can refer to the evaluation code and metric code for details :)

Thank you for your reply. How can I train on the Cityscapes dataset?

ruili3 commented 8 months ago

Just make sure you can get the GT pose for this dataset, and then you can organize the data in a way similar to the KITTI odometry dataset