search

city-super / BungeeNeRF

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

Rendering the results #9

Closed bycloudai closed 2 years ago

bycloudai commented 2 years ago

Hi, thank you for sharing the codes of your amazing research!

Just curious, right now I am using the default render poses_enu.json file, and it only produces 29 frames. How can I generate one from a custom .esp from Google Earth and convert that into poses_enu.json file? I understand you wrote a description about how to convert it and such, but I think I am failing to replicate that. Any help would be appreciated!

kam1107 commented 2 years ago

Hi, I newly added a sample script of how we generally convert GES camera data to poses: https://github.com/city-super/BungeeNeRF/blob/main/GES2pose.py

bycloudai commented 2 years ago

Hi thank you so much for your response, the script works perfectly! However, it doesn't seem to be able to adjust to make it output more than 29 frames, do you mind sharing how I can control that? Thank you.

bycloudai commented 2 years ago

nvm I figured it out. After specifying the argument --holdout 1 it worked. Thank you