NeRFPlayer#
A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields
Installation#
First install nerfstudio dependencies. Then run:
pip install git+https://github.com/lsongx/nerfplayer-nerfstudio.git
Running NeRFPlayer#
Details for running NeRFPlayer can be found here. Once installed, run:
ns-train nerfplayer-ngp --help
Two variants of NeRFPlayer are provided:
Method |
Description |
---|---|
|
NeRFPlayer with nerfacto backbone |
|
NeRFPlayer with instant-ngp-bounded backbone |
Method Overview#
First, we propose to decompose the 4D spatiotemporal space according to temporal characteristics. Points in the 4D space are associated with probabilities of belonging to three categories: static, deforming, and new areas. Each area is represented and regularized by a separate neural field. Second, we propose a hybrid representations based feature streaming scheme for efficiently modeling the neural fields.
Please see TODO lists to see the unimplemented components in the nerfstudio based version.