search

noahzn / Lite-Mono

[CVPR2023] Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation
MIT License
540 stars 61 forks source link

How do I set camera parameters when recovering point clouds from depth maps? #21

Closed xiakunwonder closed 1 year ago

xiakunwonder commented 1 year ago

I used my own image data as input. How do I set the camera parameters? To recover the three-dimensional point cloud

noahzn commented 1 year ago

Hi, For the training you need to change the camera intrinsic. Please check this issue.

If you already have the generated depth maps and want to convert them into point clouds, you still need the intrinsic of the camera. However, I haven't tried to do this.

noahzn commented 1 year ago

Hi, I am now closing this issue due to no response. You can reopen it if you want to give any updates.