ngp_pl

Advertisement: stay tuned with my channel, I will upload cuda tutorials recently, and do a stream about this implementation!

Instant-ngp (only NeRF) in pytorch+cuda trained with pytorch-lightning (high quality with high speed). This repo aims at providing a concise pytorch interface to facilitate future research, and am grateful if you can share it (and a citation is highly appreciated)!

• Official CUDA implementation
• torch-ngp another pytorch implementation that I highly referenced.

:paintbrush: Gallery

https://user-images.githubusercontent.com/11364490/181671484-d5e154c8-6cea-4d52-94b5-1e5dd92955f2.mp4

Other representative videos are in GALLERY.md

:computer: Installation

This implementation has strict requirements due to dependencies on other libraries, if you encounter installation problem due to hardware/software mismatch, I'm afraid there is no intention to support different platforms (you are welcomed to contribute).

Hardware

• OS: Ubuntu 20.04
• NVIDIA GPU with Compute Compatibility >= 75 and memory > 6GB (Tested with RTX 2080 Ti), CUDA 11.3 (might work with older version)
• 32GB RAM (in order to load full size images)

Software

• Clone this repo by git clone https://github.com/kwea123/ngp_pl

• Python>=3.8 (installation via anaconda is recommended, use conda create -n ngp_pl python=3.8 to create a conda environment and activate it by conda activate ngp_pl)

• Python libraries

  • Install pytorch>=1.11.0 by pip install torch torchvision --extra-index-url https://download.pytorch.org/whl/cu113
  • Install torch-scatter following their instruction
  • Install tinycudann following their instruction (compilation and pytorch extension)
  • Install apex following their instruction
  • Install core requirements by pip install -r requirements.txt

• Cuda extension: Upgrade pip to >= 22.1 and run pip install models/csrc/ (please run this each time you pull the code)

:books: Supported Datasets

1. NSVF data

Download preprocessed datasets (Synthetic_NeRF, Synthetic_NSVF, BlendedMVS, TanksAndTemples) from NSVF. Do not change the folder names since there is some hard-coded fix in my dataloader.

2. NeRF++ data

Download data from here.

3. Colmap data

For custom data, run colmap and get a folder sparse/0 under which there are cameras.bin, images.bin and points3D.bin. The following data with colmap format are also supported:

• nerf_llff_data
• mipnerf360 data
• HDR-NeRF data. Additionally, download my colmap pose estimation from here and extract to the same location.

4. RTMV data

Download data from here. To convert the hdr images into ldr images for training, run python misc/prepare_rtmv.py <path/to/RTMV>, it will create images/ folder under each scene folder, and will use these images to train (and test).

:key: Training

Quickstart: python train.py --root_dir <path/to/lego> --exp_name Lego

It will train the Lego scene for 30k steps (each step with 8192 rays), and perform one testing at the end. The training process should finish within about 5 minutes (saving testing image is slow, add --no_save_test to disable). Testing PSNR will be shown at the end.

More options can be found in opt.py.

For other public dataset training, please refer to the scripts under benchmarking.

:mag_right: Testing

Use test.ipynb to generate images. Lego pretrained model is available here

GUI usage: run python show_gui.py followed by the same hyperparameters used in training (dataset_name, root_dir, etc)

Comparison with torch-ngp and the paper

I compared the quality (average testing PSNR on Synthetic-NeRF) and the inference speed (on Lego scene) v.s. the concurrent work torch-ngp (default settings) and the paper, all trained for about 5 minutes:

As for quality, mine is slightly better than torch-ngp, but the result might fluctuate across different runs.

As for speed, mine is faster than torch-ngp, but is still only half fast as instant-ngp. Speed is dependent on the scene (if most of the scene is empty, speed will be faster).

^{Left: torch-ngp. Right: mine.}

:chart: Benchmarks

To run benchmarks, use the scripts under benchmarking.

Followings are my results trained using 1 RTX 2080 Ti (qualitative results here):

TODO

• [ ] use super resolution in GUI to improve FPS
• [ ] multi-sphere images as background