search

city-super / BungeeNeRF

[ECCV22] BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering
https://city-super.github.io/citynerf
MIT License
565 stars 61 forks source link

How to easily generate the rendering trajactories when evaluation? #7

Closed Wei-Baldwin-Zeng closed 2 years ago

Wei-Baldwin-Zeng commented 2 years ago

Hi, Amazing work!!!!!

How can I generate the rendering trajactories when I'm trying to evaluate the trained model? I couldn't find an easy way to do that.

Looking forward to your reply.

kam1107 commented 2 years ago

To evaluate the model trained on the provided dataset, you should use the test set. If you are trying to render a new trajectory, the easiest way is to create one in Google Earth Studio and use the generated cam poses.

Wei-Baldwin-Zeng commented 2 years ago

Thank you for your reply.

Yes, using the test set to evaluate the trained model, which I can understand, because you need the gt to calculate the PSNR, right?

When I have finished training, if I just want to play around the trained model, is there any way to create a new rendering trajectory for me to render new views (or even just create some new rendering view points it's ok) , besides using Google Earth Studio to create one?

kam1107 commented 2 years ago

In our setting, we transformed the coordinate system into ENU (https://en.wikipedia.org/wiki/Local_tangent_plane_coordinates) with the origin set to the center building. If you don't want to use GES you can also mathematically calculate a curve.