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

Camera trace failed on custom dataset #77

Open
Contrail97 opened this issue Feb 26, 2024 · 2 comments
Open

Camera trace failed on custom dataset #77

Contrail97 opened this issue Feb 26, 2024 · 2 comments
Labels
question Further information is requested

Comments

@Contrail97
Copy link

First of all, thank you for your research, which has been very inspiring to me. I found the reconstruction results obtained using your project on the replica dataset satisfactory. However, I encountered some issues when working with a custom dataset. Due to certain reasons, I couldn't use the online or offline modes of NerfCapture. Therefore, I used Polycam instead of NerfCapture to capture scenes and generate depth, RGB, and transforms.json.

Then I modified the following config in file configs/iphone/splatam.py:
base_dir = "./data"
scene_name = "poly1"
num_frames = 188

And use the following instructions to reconstruct the scene
python scripts/splatam.py configs/iphone/splatam.py

When I set the use_gt_poses = True, I found that the reconstructed room barely met its original geometric constraints:
image

But when I set the use_gt_poses = False, I noticed that the reconstructed scenes were starting to look strange:
Weixin Screenshot_20240226095804
Weixin Screenshot_20240226095307
It looks like a spiral that strings together each trained rgb image on the line,i.e. the camera's pose estimate has shifted a lot.

At first, I thought there was something wrong with the depth map, so I opened the eval directory to see the evaluation screenshot:

![0000](https://github.com/spla-tam/SplaTA
0050
M/assets/28862680/079a0e1c-a0da-498d-becf-609b3e49cd22)
0062

From the screenshot above it looks like there's nothing wrong with the depth map.
So I don't know, where did I go wrong? If there is any suggestion I will be very appreciated.

I also upload my custom dataset on Google to reproduce the issue.
https://drive.google.com/file/d/1ogvhCim9vXZjVK0EpqAqTat93bAbUblp/view?usp=sharing

Thanks, look forward to your reply.

@Zhangyangrui916
Copy link

When i set the use_gt_poses = True, I fix wrong camera pose in my custom dataset, which takes me several days to solve……
I wonder why use_gt_poses default value is False ?

You can try my dataset to see if it work
https://pan.baidu.com/s/1gsUwh0x9pH2cy78G97JjUg?pwd=gljt

i captured this data with a modified version of NerfCapture, you can check my repo

@Nik-V9
Copy link
Contributor

Nik-V9 commented Mar 14, 2024

Hi, Thanks for trying the code out with Polycam data!

I think the tracking is failing because the images are sideways. I would recommend orienting them correctly and trying.

@Nik-V9 Nik-V9 added the question Further information is requested label Mar 14, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

3 participants