Home

Awesome

<p align="left"> <!-- PyPi badge --> <a href="https://badge.fury.io/py/kplanes-nerfstudio"><img src="https://badge.fury.io/py/kplanes-nerfstudio.svg" alt="PyPI version"></a> <!-- License badge --> <a href="LICENSE.txt"> <img alt="license" src="https://img.shields.io/badge/license-BSD-blue"> </a> </p>

K-Planes nerfstudio integration

This repository provides code to integrate the K-Planes model into nerfstudio.

<div align='center'> <img src="https://sarafridov.github.io/K-Planes/assets/intro_figure.jpg" height="200px"/> </div>

It provides an alternative way to use k-planes in addition to the official repository, which allows access to nerfstudio's in-browser viewer and additional training capabilities. Beware that some details about the training procedure differ from the official repository.

Installation

  1. Install nerfstudio. This is pip install nerfstudio, but there are a few dependencies (e.g. torch, tinycudann) which may require further steps, so make sure to check their installation guide!
  2. Install the k-planes nerfstudio integration (this repository): pip install kplanes-nerfstudio

Included Models

Two models are included here:

:exclamation: PRs are welcome for configurations tuned to different datasets :exclamation:

You can run the static model by calling (remember to use the correct data directory!)

ns-train kplanes --data <data-folder>

and connect to the viewer using the link provided in the output of the training script.

Benchmarks

Synthetic NeRF (hybrid model)

drumsmaterialsficusshipmicchairlegohotdogAVG
PSNR26.3129.8232.4730.2733.7334.9836.5636.7732.61
SSIM0.93940.95390.97880.87550.98570.98240.9820.97920.9596

DNeRF (hybrid model)

hell warriormutanthookballslegot-rexstand upjumping jacksAVG
PSNR25.0634.2928.2243.0227.0333.5934.0433.4332.33
SSIM0.94870.98390.95520.99540.9560.98170.98350.97970.973

Roadmap

Expected future updates to this repository: