nerfstudio/docs/nerfology/methods/nerfplayer.md

NeRFPlayer

A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields

:color: primary
:outline:
Paper Website

:color: primary
:outline:
Nerfstudio add-on code

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-nerfacto	NeRFPlayer with nerfacto backbone
nerfplayer-ngp	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.