"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

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models.

Real-CUGAN - Real Cascade U-Nets for Anime Image Super Resolution

Official repository for HOTR: End-to-End Human-Object Interaction Detection with Transformers (CVPR'21, Oral Presentation)

PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition"

Get the partition that a file belongs and the percentage of space that consumes

🛰️ List of earth observation companies and job sites

Real-Time Multi-Contact Model Predictive Control via ADMM

Free-duolingo-plus - Duolingo account creator that uses your invite code to get you free duolingo plus

AugLy is a data augmentations library that currently supports four modalities (audio, image, text & video) and over 100 augmentations

ESTDepth: Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks (CVPR 2021)

Python package for covariance matrices manipulation and Biosignal classification with application in Brain Computer interface

The official implementation of NeurIPS 2021 paper: Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

Serving PyTorch 1.0 Models as a Web Server in C++

Implementations of LSTM: A Search Space Odyssey variants and their training results on the PTB dataset.

Segmentation vgg16 fcn - cityscapes

Serverless proxy for Spark cluster

Deep Learning pipeline for motor-imagery classification.

Implementation for the paper: Invertible Denoising Network: A Light Solution for Real Noise Removal (CVPR2021).

Repository for Traffic Accident Benchmark for Causality Recognition (ECCV 2020)