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

请问要如何修改相机模型,让它支持主点不在图像中心的数据 #69

Open
JimmyJune opened this issue Dec 6, 2024 · 3 comments

Comments

@JimmyJune
Copy link

JimmyJune commented Dec 6, 2024

作者您好,十分感谢您的工作。我想修改相机模型,让它支持主点不在中心的相机。
我已经修改render ,将cx,cy 传入渲染器中,但是迭代7000次之后会就出现问题。
pastedImage
绿线是修改后的结果,另外两条曲线是修改之前的曲线,和原生3dgs 修改后的loss曲线。
image
image
这个是log 中图片效果

@danpeng2
Copy link
Contributor

danpeng2 commented Dec 6, 2024

您好,这块还没尝试过。您先确认下camera.py中的相机内参是否正常,尝试下先把单视图和多视图几何正则项关掉,这样和原始3DGS版本接近,先确认这个接近版本是否有问题?

@SuperXia123
Copy link

@JimmyJune Hopefully the discussion here could help.

@JimmyJune
Copy link
Author

我改了相机模型支持cx,cy不在中心的情况,测试了gof,mip-splatting 等方法,都是可以收敛的。 关闭掉multi_view_weight_from_iter,就可以收敛了,如果增加回去,当训练7000iter 之后就会出翔不收敛的情况

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

3 participants