"SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image", Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, Zhangyang Wang

Last update: Jan 05, 2023

Overview

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

[Paper] [Website]

Pipeline

Code

Environment

pip install -r requirements.txt

Dataset Preparation

Please download the datasets from these links:

NeRF synthetic: Download nerf_synthetic.zip from https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1
LLFF: Download nerf_llff_data.zip from https://drive.google.com/drive/folders/128yBriW1IG_3NJ5Rp7APSTZsJqdJdfc1
DTU: Download the preprocessed DTU training data from https://drive.google.com/file/d/1eDjh-_bxKKnEuz5h-HXS7EDJn59clx6V/view

Please download the depth from here: https://drive.google.com/drive/folders/13Lc79Ox0k9Ih2o0Y9e_g_ky41Nx40eJw?usp=sharing

Training

If you meet OOM issue, try:

enable precision=16
reduce the patch size --patch_size (or --patch_size_x, --patch_size_y) and enlarge the stride size --sH, --sW

NeRF synthetic

Step 1

python train.py  --dataset_name blender_ray_patch_1image_rot3d  --root_dir  ../../dataset/nerf_synthetic/lego   --N_importance 64 --img_wh 400 400 --num_epochs 3000 --batch_size 1  --optimizer adam --lr 2e-4  --lr_scheduler steplr --decay_step 1000 2000 --decay_gamma 0.5  --exp_name lego_s6 --with_ref --patch_size 64 --sW 6 --sH 6 --proj_weight 1 --depth_smooth_weight 0  --dis_weight 0 --num_gpus 4 --load_depth --depth_type nerf --model sinnerf --depth_weight 8 --vit_weight 10 --scan 4

Step 2

python train.py  --dataset_name blender_ray_patch_1image_rot3d  --root_dir  ../../dataset/nerf_synthetic/lego   --N_importance 64 --img_wh 400 400 --num_epochs 3000 --batch_size 1  --optimizer adam --lr 1e-4  --lr_scheduler steplr --decay_step 1000 2000 --decay_gamma 0.5  --exp_name lego_s6_4ft --with_ref --patch_size 64 --sW 4 --sH 4 --proj_weight 1 --depth_smooth_weight 0.1  --dis_weight 0.1 --num_gpus 4 --load_depth --depth_type nerf --model sinnerf --depth_weight 8 --vit_weight 0 --pt_model xxx.ckpt --nerf_only  --scan 4

LLFF

Step 1

python train.py  --dataset_name llff_ray_patch_1image_proj  --root_dir  ../../dataset/nerf_llff_data/room   --N_importance 64 --img_wh 504 378 --num_epochs 3000 --batch_size 1  --optimizer adam --lr 2e-4  --lr_scheduler steplr --decay_step 1000 2000 --decay_gamma 0.5  --exp_name llff_room_s4 --with_ref --patch_size_x 63 --patch_size_y 84 --sW 4 --sH 4 --proj_weight 1 --depth_smooth_weight 0  --dis_weight 0 --num_gpus 4 --load_depth --depth_type nerf --model sinnerf --depth_weight 8 --vit_weight 10

Step 2

python train.py  --dataset_name llff_ray_patch_1image_proj  --root_dir  ../../dataset/nerf_llff_data/room   --N_importance 64 --img_wh 504 378 --num_epochs 3000 --batch_size 1  --optimizer adam --lr 1e-4  --lr_scheduler steplr --decay_step 1000 2000 --decay_gamma 0.5  --exp_name llff_room_s4_2ft --with_ref --patch_size_x 63 --patch_size_y 84 --sW 2 --sH 2 --proj_weight 1 --depth_smooth_weight 0.1  --dis_weight 0.1 --num_gpus 4 --load_depth --depth_type nerf --model sinnerf --depth_weight 8 --vit_weight 0 --pt_model xxx.ckpt --nerf_only

DTU

Step 1

python train.py  --dataset_name dtu_proj  --root_dir  ../../dataset/mvs_training/dtu   --N_importance 64 --img_wh 640 512 --num_epochs 3000 --batch_size 1  --optimizer adam --lr 2e-4  --lr_scheduler steplr --decay_step 1000 2000 --decay_gamma 0.5  --exp_name dtu_scan4_s8 --with_ref --patch_size_y 70 --patch_size_x 56 --sW 8 --sH 8 --proj_weight 1 --depth_smooth_weight 0  --dis_weight 0 --num_gpus 4 --load_depth --depth_type nerf --model sinnerf --depth_weight 8 --vit_weight 10 --scan 4

Step 2

python train.py  --dataset_name dtu_proj  --root_dir  ../../dataset/mvs_training/dtu   --N_importance 64 --img_wh 640 512 --num_epochs 3000 --batch_size 1  --optimizer adam --lr 1e-4  --lr_scheduler steplr --decay_step 1000 2000 --decay_gamma 0.5  --exp_name dtu_scan4_s8_4ft --with_ref --patch_size_y 70 --patch_size_x 56 --sW 4 --sH 4 --proj_weight 1 --depth_smooth_weight 0.1  --dis_weight 0.1 --num_gpus 4 --load_depth --depth_type nerf --model sinnerf --depth_weight 8 --vit_weight 0 --pt_model xxx.ckpt --nerf_only  --scan 4

More finetuning with smaller strides benefits reconstruction quality.

Testing

python eval.py  --dataset_name llff  --root_dir /dataset/nerf_llff_data/room --N_importance 64 --img_wh 504 378 --model nerf --ckpt_path ckpts/room.ckpt --timestamp test

Acknowledgement

Codebase based on https://github.com/kwea123/nerf_pl . Thanks for sharing!

Citation

If you find this repo is helpful, please cite:


@InProceedings{Xu_2022_SinNeRF,
author = {Xu, Dejia and Jiang, Yifan and Wang, Peihao and Fan, Zhiwen and Shi, Humphrey and Wang, Zhangyang},
title = {SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image},
journal={arXiv preprint arXiv:2204.00928},
year={2022}
}

"SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image", Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, Zhangyang Wang

Related tags

Overview

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

Pipeline

Code

Environment

Dataset Preparation

Training

Testing

Acknowledgement

Citation

Owner

VITA

A modular PyTorch library for optical flow estimation using neural networks

The personal repository of the work: DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer.

Bayesian Optimization Library for Medical Image Segmentation.

Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

An open source implementation of CLIP.

Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)

Unrolled Generative Adversarial Networks

Code for the SIGIR 2022 paper "Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion"

SegNet model implemented using keras framework

PyTorch implementation of the YOLO (You Only Look Once) v2

Causal estimators for use with WhyNot

Create Own QR code with Python

Consistency Regularization for Adversarial Robustness

MAGMA - a GPT-style multimodal model that can understand any combination of images and language

Agent-based model simulator for air quality and pandemic risk assessment in architectural spaces

Source code release of the paper: Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation.

The source code and data of the paper "Instance-wise Graph-based Framework for Multivariate Time Series Forecasting".

Data and code from COVID-19 machine learning paper

Code for "Adversarial Attack Generation Empowered by Min-Max Optimization", NeurIPS 2021

YOLO-v5 기반 단안 카메라의 영상을 활용해 차간 거리를 일정하게 유지하며 주행하는 Adaptive Cruise Control 기능 구현

"SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image", Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Humphrey Shi, Zhangyang Wang

Related tags

Overview

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

Pipeline

Code

Environment

Dataset Preparation

Training

Testing

Acknowledgement

Citation

Owner

VITA

A modular PyTorch library for optical flow estimation using neural networks

The personal repository of the work: *DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer*.

Bayesian Optimization Library for Medical Image Segmentation.

Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

An open source implementation of CLIP.

Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)

Unrolled Generative Adversarial Networks

Code for the SIGIR 2022 paper "Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion"

SegNet model implemented using keras framework

PyTorch implementation of the YOLO (You Only Look Once) v2

Causal estimators for use with WhyNot

Create Own QR code with Python

Consistency Regularization for Adversarial Robustness

MAGMA - a GPT-style multimodal model that can understand any combination of images and language

Agent-based model simulator for air quality and pandemic risk assessment in architectural spaces

Source code release of the paper: Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation.

The source code and data of the paper "Instance-wise Graph-based Framework for Multivariate Time Series Forecasting".

Data and code from COVID-19 machine learning paper

Code for "Adversarial Attack Generation Empowered by Min-Max Optimization", NeurIPS 2021

YOLO-v5 기반 단안 카메라의 영상을 활용해 차간 거리를 일정하게 유지하며 주행하는 Adaptive Cruise Control 기능 구현

The personal repository of the work: DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer.