zhenpeiyang/MVS2D zhenpeiyang/MVS2D

  • Stars
    star
    123
  • Rank 290,145 (Top 6 %)
  • Language
    Python
  • Created over 3 years ago
  • Updated about 2 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
zhenpeiyang/MVS2D
github

zhenpeiyang

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions

Project Page | Paper


drawing

If you find our work useful for your research, please consider citing our paper:

@article{DBLP:journals/corr/abs-2104-13325,
  author    = {Zhenpei Yang and
               Zhile Ren and
               Qi Shan and
               Qixing Huang},
  title     = {{MVS2D:} Efficient Multi-view Stereo via Attention-Driven 2D Convolutions},
  journal   = {CoRR},
  volume    = {abs/2104.13325},
  year      = {2021},
  url       = {https://arxiv.org/abs/2104.13325},
  eprinttype = {arXiv},
  eprint    = {2104.13325},
  timestamp = {Tue, 04 May 2021 15:12:43 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2104-13325.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

✏️ Changelog

Nov 27 2021

  • Initial release. Note that our released code achieve improved results than those reported in the initial arxiv pre-print. In addition, we include the evaluation on DTU dataset. We will update our paper soon.

βš™οΈ Installation

Click to expand

The code is tested with CUDA10.1. Please use following commands to install dependencies:

conda create --name mvs2d python=3.7
conda activate mvs2d

pip install -r requirements.txt

The folder structure should looks like the following if you have downloaded all data and pretrained models. Download links are inside each dataset tab at the end of this README.

.
β”œβ”€β”€ configs
β”œβ”€β”€ datasets
β”œβ”€β”€ demo
β”œβ”€β”€ networks
β”œβ”€β”€ scripts
β”œβ”€β”€ pretrained_model
β”‚Β Β  β”œβ”€β”€ demon
β”‚Β Β  β”œβ”€β”€ dtu
β”‚Β Β  └── scannet
β”œβ”€β”€ data
β”‚Β Β  β”œβ”€β”€ DeMoN
β”‚Β Β  β”œβ”€β”€ DTU_hr
β”‚Β Β  β”œβ”€β”€ SampleSet
β”‚Β Β  β”œβ”€β”€ ScanNet
β”‚Β Β  └── ScanNet_3_frame_jitter_pose.npy
β”œβ”€β”€ splits
β”‚Β Β  β”œβ”€β”€ DeMoN_samples_test_2_frame.npy
β”‚Β Β  β”œβ”€β”€ DeMoN_samples_train_2_frame.npy
β”‚Β Β  β”œβ”€β”€ ScanNet_3_frame_test.npy
β”‚Β Β  β”œβ”€β”€ ScanNet_3_frame_train.npy
β”‚Β Β  └── ScanNet_3_frame_val.npy

🎬 Demo

Click to expand

After downloading the pretrained models for ScanNet, try to run following command to make a prediction on a sample data.

python demo.py --cfg configs/scannet/release.conf

The results are saved as demo.png

⏳ Training & Testing

We use 4 Nvidia V100 GPU for training. You may need to modify 'CUDA_VISIBLE_DEVICES' and batch size to accomodate your GPU resources.

ScanNet

Click to expand

Download

data πŸ”— split πŸ”— pretrained models πŸ”— noisy pose πŸ”—

Training

First download and extract ScanNet training data and split. Then run following command to train our model.

bash scripts/scannet/train.sh

To train the multi-scale attention model, add --robust 1 to the training command in scripts/scannet/train.sh.

To train our model with noisy input pose, add --perturb_pose 1 to the training command in scripts/scannet/train.sh.

Testing

First download and extract data, split and pretrained models.

Then run:

bash scripts/scannet/test.sh

You should get something like these:

abs_rel sq_rel log10 rmse rmse_log a1 a2 a3 abs_diff abs_diff_median thre1 thre3 thre5
0.059 0.016 0.026 0.157 0.084 0.964 0.995 0.999 0.108 0.079 0.856 0.974 0.996

SUN3D/RGBD/Scenes11

Click to expand

Download

data πŸ”— split πŸ”— pretrained models πŸ”—

Training

First download and extract DeMoN training data and split. Then run following command to train our model.

bash scripts/demon/train.sh

Testing

First download and extract data, split and pretrained models.

Then run:

bash scripts/demon/test.sh

You should get something like these:

dataset rgbd: 160

abs_rel sq_rel log10 rmse rmse_log a1 a2 a3 abs_diff abs_diff_median thre1 thre3 thre5
0.082 0.165 0.047 0.440 0.147 0.921 0.939 0.948 0.325 0.284 0.753 0.894 0.933

dataset scenes11: 256

abs_rel sq_rel log10 rmse rmse_log a1 a2 a3 abs_diff abs_diff_median thre1 thre3 thre5
0.046 0.080 0.018 0.439 0.107 0.976 0.989 0.993 0.155 0.058 0.822 0.945 0.979

dataset sun3d: 160

abs_rel sq_rel log10 rmse rmse_log a1 a2 a3 abs_diff abs_diff_median thre1 thre3 thre5
0.099 0.055 0.044 0.304 0.137 0.893 0.970 0.993 0.224 0.171 0.649 0.890 0.969

-> Done!

depth

abs_rel sq_rel log10 rmse rmse_log a1 a2 a3 abs_diff abs_diff_median thre1 thre3 thre5
0.071 0.096 0.033 0.402 0.127 0.938 0.970 0.981 0.222 0.152 0.755 0.915 0.963

DTU

Click to expand

Download

data πŸ”— eval data πŸ”— eval toolkit πŸ”— pretrained models πŸ”—

Training

First download and extract DTU training data. Then run following command to train our model.

bash scripts/dtu/test.sh

Testing

First download and extract DTU eval data and pretrained models.

The following command performs three steps together: 1. Generate depth prediction on DTU test set. 2. Fuse depth predictions into final point cloud. 3. Evaluate predicted point cloud. Note that we re-implement the original Matlab Evaluation of DTU dataset using python.

bash scripts/dtu/test.sh

You should get something like these:

Acc 0.4051747996189477
Comp 0.2776021161518006
F-score 0.34138845788537414

Acknowledgement

The fusion code for DTU dataset is heavily built upon from PatchMatchNet

More Repositories

1

RelativePose

Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion
Python
149
star
2

HM3D-ABO

Python
85
star
3

FvOR

FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction
Python
54
star
4

pytorch-learned-correspondence

original tensorflow impl: https://github.com/vcg-uvic/learned-correspondence-release
Python
5
star