Here is the official repository of our paper "Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking" (ECCV2020 Spotlight).
./conda_install.sh
MVS_TRANING
folder.dtu_data_root
to your MVS_TRAINING
path in env.sh
Create a log folder and a model folder in wherever you like to save the training outputs. Set the log_dir
and save_dir
in train.sh
correspondingly../train.sh
DTU_TESTING
path or TP_TESTING
path for testing in env.sh
.MODEL_FOLDER
to ckpt
and model_ckpt_index
to checkpoint_list
to choose pretrained model../eval_dtu.sh
for DTU, or ./eval_tanks.sh
for Tanks and Temples../fusion.sh
for DTU or Tanks and Temples.Acc. | Comp. | Overall. |
---|---|---|
0.395 | 0.378 | 0.386 |
D2HC-RMVSNet point cloud results are provided: DTU evaluation point clouds.
Evaluate the point clouds using the DTU evaluation code.
Mean | Family | Francis | Horse | Lighthouse | M60 | Panther | Playground | Train |
---|---|---|---|---|---|---|---|---|
59.20 | 74.69 | 56.04 | 49.42 | 60.08 | 59.81 | 59.61 | 60.04 | 53.92 |
As shown on Tanks and Temples leaderboard.
The corresponding point cloud is provided: BlendedMVS result.
The rest reconstructed point clouds of the validation dataset of BlendedMVS are also provided.
If you find this project useful for your research, please cite:
@inproceedings{yan2020dense,
title={Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking},
author={Yan, Jianfeng and Wei, Zizhuang and Yi, Hongwei and Ding, Mingyu and Zhang, Runze and Chen, Yisong and Wang, Guoping and Tai, Yu-Wing},
booktitle={ECCV},
year={2020}
}
Add pretrained model on BlendedMVS.