search

fangchangma / self-supervised-depth-completion

ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and Monocular Camera"
MIT License
623 stars 135 forks source link

About result visualization #27

Open WANGYINGYU opened 5 years ago

WANGYINGYU commented 5 years ago

image Hello, In the evaluation results, I found that there is content about the visualization of the results, as shown in the picture. What I don't know is what the fourth column is. It seems to be a semi-dense depth map of the annotations, but I used the self-supervised mode(sparse+photo), which should not use annotation data. Can you answer my doubts? Thank you.

WANGYINGYU commented 5 years ago

@fangchangma

fangchangma commented 5 years ago

You were correct about the rightmost column being the semi-dense annotations (i.e., gt in the following line). https://github.com/fangchangma/self-supervised-depth-completion/blob/b8140669c2ff7658509edd39f5a73638b78d214b/main.py#L101

The fourth column is currently part of the visualization, regardless of how the network is being trained.

nowburn commented 4 years ago

@fangchangma Hello, I'm glad to see your paper, it's really a good job.

2019icra How do you generate it ? Is it a real street 3D model? if so , can you share your code to my email(newcoding@163.com)? Thanks a lot!