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.

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

How to visualize the depth file? #20

Open
TongWeiDP opened this issue Dec 10, 2020 · 5 comments
Open

How to visualize the depth file? #20

TongWeiDP opened this issue Dec 10, 2020 · 5 comments

Comments

@TongWeiDP
Copy link

The depth files,such as depth_map_0002.pfm in the file of DTU training,how to visualize it?What software is used to achieve it? or using the code to visualize it ?

@XYZ-qiyh
Copy link

XYZ-qiyh commented Dec 10, 2020

You can use the python script visualize.py provided by original MVSNet.
Also you can use https://github.com/Todd-Qi/MVSNet-PyTorch/blob/master/tools/gray2color.py

@TongWeiDP
Copy link
Author

You can use the python script visualize.py provided by original MVSNet.
Also you can use https://github.com/Todd-Qi/MVSNet-PyTorch/blob/master/tools/gray2color.py

Hello,I trained the UCSNET network which is based on the Mvsnet network,but I encountered a problem that the loss is very high when I first started training without the pretrained model,the batch_size is one,num_gpus is one. I cannot get the author's reply,I am eager to find the the reason about it.my training parameters is same as the author's code. Have you trained the UCSNET network before? Waiting for your reply.Thanks.

@XQQ1072448274
Copy link

您好,想问下可视化深度图文件时,采用这个visualize.py时,我仅仅修改了parser.add_argument('depth_path',default='./depth_est/')
但是我并没有得到看到生成的深度图文件

@kk6398
Copy link

kk6398 commented Oct 29, 2022

你好,我也是遇到了相同的问题,请问你找到解决的办法了吗?

@TongWeiDP
Copy link
Author

TongWeiDP commented Oct 29, 2022 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants