By Abdullah Hamdi, Bernard Ghanem, Matthias Nießner
The official Pytroch code of the paper SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images. SPARF is a large-scale sparse radiance field dataset consisting of ~ 1 million SRFs with multiple voxel resolutions (32, 128, and 512) and 17 million posed images with a resolution of 400 X 400. Furthermore, we propose SuRFNet, a pipline to generate SRFs conditioned on input images, achieving SOTA on ShapeNet novel views synthesis from one or few input images.
To start, we prefer creating the environment using conda:
conda env create -f environment.yml
conda activate sparfPlease make sure you have up-to-date NVIDIA drivers supporting CUDA 11.3 at least.
Alternatively use pip -r requirements.txt.
The dataset is released in the link. Each of SPARF's classes has the same structure of NeRF-synthetic dataset and can be loaded similarly. Download all content in the link and place inside data/SPARF_images. Then you can run the notebook example.
If you find our work useful in your research, please consider citing:
@InProceedings{hamdi2022sparf,
author = {Hamdi, Abdullah and Ghanem, Bernard and Nie{\ss}ner, Matthias},
title = {SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images},
publisher = {arxiv},
year = {2022},
}