Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

About the stage1 training #20

Closed
OrangeSodahub opened this issue Apr 7, 2023 · 1 comment
Closed

About the stage1 training #20

OrangeSodahub opened this issue Apr 7, 2023 · 1 comment

Comments

@OrangeSodahub
Copy link

OrangeSodahub commented Apr 7, 2023 •
edited

According to your paper:
image
You output the query proposal based on the depth prediction, however I saw in your released code that you used LMSCNet to generate the proposal, is it a misalignment? It seems that LMSCNet didn't generate a depth prediction, but got lidar input and output the class-specified results. Look forward to your reply!
@RoboticsYimingLi
Copy link
Contributor

RoboticsYimingLi commented May 8, 2023 •
edited

Our query proposal network employs LMSCNet, which takes depth as input and produces 3D occupancy as output. The input depth is obtained from a readily available monocular or binocular depth model. Please refer to Section 3.4 for more details.

@Ha-coding-user Ha-coding-user mentioned this issue Apr 19, 2024
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@RoboticsYimingLi @OrangeSodahub