search

autonomousvision / giraffe

This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"
https://m-niemeyer.github.io/project-pages/giraffe/index.html
MIT License
1.23k stars 160 forks source link

About the number of NeRF #55

Open xiaobiaodu opened 11 months ago

xiaobiaodu commented 11 months ago

Hi

Thanks for your excellent work! I have some details that make me confused and I may need your further explanation if you are available. You mentioned in your paper that you use N NeRFs to disentangle different foreground and background. But I find that you only use one NeRF(named "decoder" in your code) to achieve this. That's different from your paper, right?

By the way, could you please explain why NeRF can disentangle the objects and background and achieve the segmentation result?

image