TiNeuVox

TiNeuVox copied to clipboard

This is the code implementation of https://arxiv.org/abs/2205.15285

Our method converges very quickly. This is a comparison between D-NeRF (left) and our method (right).

We propose a radiance field framework by representing scenes with time-aware voxel features. A tiny coordinate deformation network is introduced to model coarse motion trajectories and temporal information is further enhanced in the radiance network. A multi-distance interpolation method is proposed and applied on voxel features to model both small and large motions. Our framework significantly accelerates the optimization of dynamic radiance fields while maintaining high rendering quality. Empirical evaluation is performed on both syntheticand real scenes. Our method completes training with only 8 minutes and 8-MB storage cost while showing similar or even better rendering performance than previous dynamic NeRF methods.

Notes

• May. 31, 2022 The first and preliminary version is realeased. Code may not be cleaned thoroughly, so feel free to open an issue if any question.

Requirements

• lpips
• mmcv
• imageio
• imageio-ffmpeg
• opencv-python
• pytorch_msssim
• torch
• torch_scatter

Data Preparation

For synthetic scenes:
The dataset provided in D-NeRF is used. You can download the dataset from dropbox. Then organize your dataset as follows.

├── data_dnerf 
│   ├── mutant
│   ├── standup 
│   ├── ...

For real dynamic scenes:
The dataset provided in HyperNeRF is used. You can download scenes from Hypernerf Dataset and organize them as Nerfies.

Training

For training synthetic scenes such as standup, run

python run.py --config configs/nerf-*/standup.py 

Use small for TiNeuVox-S and base for TiNeuVox-B. Use --render_video to render a video.

For training real scenes such as vrig_chicken, run

python run.py --config configs/vrig_dataset/chicken.py  

Evaluation

Run the following script to evaluate the model.

For synthetic ones:

python run.py --config configs/nerf-small/standup.py --render_test --render_only --eval_psnr --eval_lpips_vgg --eval_ssim 

For real ones:

python run.py --config configs/vrig_dataset/chicken.py --render_test --render_only --eval_psnr

To fairly compare with values reported in D-NeRF, metric.py is provided to directly evaluate the rendered images with uint8 values.

Main Results

Please visit our video for more rendered videos.

Synthetic Scenes

Real Dynamic Scenes

Acknowledgements

This repository is partially based on DirectVoxGO and D-NeRF. Thanks for their awesome works.

Citation

If you find this repository/work helpful in your research, welcome to cite the paper and give a ⭐.