PyTorch Implementation of MVSNet
MVSNet: Depth Inference for Unstructured Multi-view Stereo. Yao Yao, Zixin Luo, Shiwei Li, Tian Fang, Long Quan. ECCV 2018. MVSNet is a deep learning architecture for depth map inference from unstructured multi-view images.
This is an unofficial Pytorch implementation of MVSNet
MVS_TRANINGfolder
train.sh, set
MVS_TRAININGas your training data path
checkpoints
./train.sh
DTU_TESTINGfolder, which should contain one
camsfolder, one
imagesfolder and one
pair.txtfile.
test.sh, set
DTU_TESTINGas your testing data path and
CKPT_FILEas your checkpoint file. You can also download my pretrained model.
./test.sh
in
eval.py, I implemented a simple version of depth map fusion. Welcome contributions to improve the code.
| | Acc. | Comp. | Overall. | |-----------------------|--------|--------|----------| | MVSNet(D=256) | 0.396 | 0.527 | 0.462 | | PyTorch-MVSNet(D=192) | 0.4492 | 0.3796 | 0.4144 |
Due to the memory limit, we only train the model with
D=192, the fusion code is also different from the original repo.