This repository contains a pytorch implementation for the paper: TensoRF: Tensorial Radiance Fields. Our work present a novel approach to model and reconstruct radiance fields, which achieves super
fast training process, compact memory footprint and state-of-the-art rendering quality.
xxx.mp4
Install environment:
conda create -n TensoRF python=3.8
conda activate TensoRF
pip install torch torchvision
pip install tqdm scikit-image opencv-python configargparse lpips imageio-ffmpeg
The training script is in train.py
, we have provided command list in run_batch.py
to reproduce our results, please note:
dataset_name
, choices = ['blender', 'llff', 'nsvf', 'dtu','tankstemple'];
shadingMode
, choices = ['MLP_PE', 'SH'];
n_lamb_sigma
and n_lamb_sh
are string type refer to the basis number of density and appearance along XYZ
dimension;
N_voxel_init
and N_voxel_final
control the resolution of matrix and vector;
N_vis
and vis_every
control the visualization during training;
You need to set --render_test 1
/--render_path 1
if you want to render testing views or path after training.
More options refer to the opt.py
.
https://1drv.ms/u/s!Ard0t_p4QWIMgQ2qSEAs7MUk8hVw?e=dc6hBm,
You can just simply pass --render_only 1
and --ckpt path/to/your/checkpoint
to render images from a pre-trained
checkpoint.
If you find our code or paper helps, please consider citing:
xxx