zju3dv / ENeRF

SIGGRAPH Asia 2022: Code for "Efficient Neural Radiance Fields for Interactive Free-viewpoint Video"
https://zju3dv.github.io/enerf
Other
413 stars 28 forks source link

How to handle our own data, can you provide a tutorial? #7

Open zhangyong918 opened 1 year ago

zhangyong918 commented 1 year ago

Hello, I want to use my own data for training and rendering, how do I process my own data? In addition, in the video on your project page, can you provide interfaces and data sets for testing? I would be very grateful if a tutorial could be provided on this.

haotongl commented 1 year ago

If you're interested in processing static scenes captured by a single camera, you might find it helpful to follow the NeRF tutorial for converting the data to either LLFF format or NeRF Synthetic Format. If you're working with dynamic scenes captured by multiple synchronized cameras, the easymocap tutorial may be a good resource for preparing the data.

https://github.com/Fyusion/LLFF/blob/master/imgs2poses.py https://github.com/zju3dv/EasyMocap