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 Fix the Canonical View of the Generated 3D Model? #159

Open
alibalapour opened this issue Jan 24, 2025 · 2 comments
Open

How to Fix the Canonical View of the Generated 3D Model? #159

alibalapour opened this issue Jan 24, 2025 · 2 comments

Comments

@alibalapour
Copy link

I am using Trellis for Multi image 3d generation. However, I noticed that the initial view (canonical view) of the generated 3D .glb file is not consistent in different inputs.

I assumed that the canonical view would correspond to the first input image, but this does not seem to be the case. Is there any way to define or fix the canonical view of the output so that it aligns with the first input image or any specific view?

Any guidance on how to achieve this would be greatly appreciated!

@rainli10
Copy link

Same problem, did you find the solution yet?

@alibalapour
Copy link
Author

Well, no.

But, as I have ground-truth 3D assets, I aligned my predicted 3D assets with my ground truth with using RANSAC and ICP. It is not a proper way of solving this problem, but it works for my usage.

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

2 participants