HTensor/IGEV
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Gangwei Xu 2023-03-20 20:02:42 +08:00 committed by GitHub
parent e079f027ff
commit 150b4877c4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 33 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
README.md
View File

@ -1,5 +1,4 @@
# IGEV-Stereo & IGEV-MVS
The IGEV-MVS is coming soon.
This repository contains the source code for our paper:
@ -71,6 +70,9 @@ By default `stereo_datasets.py` will search for the datasets in these locations.
├── ETH3D
├── two_view_training
├── two_view_training_gt
├── DTU_data
├── dtu_train
├── dtu_test
```
@ -94,6 +96,22 @@ To train on KITTI, run
python train_stereo.py --restore_ckpt ./pretrained_models/sceneflow/sceneflow.pth --dataset kitti
```
## Evaluation
To evaluate on Scene Flow or Middlebury or ETH3D, run
```Shell
python evaluate_stereo.py --restore_ckpt ./pretrained_models/sceneflow/sceneflow.pth --dataset sceneflow
```
or
```Shell
python evaluate_stereo.py --restore_ckpt ./pretrained_models/sceneflow/sceneflow.pth --dataset middlebury_H
```
or
```Shell
python evaluate_stereo.py --restore_ckpt ./pretrained_models/sceneflow/sceneflow.pth --dataset eth3d
```
## Submission
For submission to the KITTI benchmark, run
@ -101,6 +119,20 @@ For submission to the KITTI benchmark, run
python save_disp.py
```
## MVS training and evaluation
To train on DTU, run
```Shell
python train_mvs.py
```
To evaluate on DTU, run
```Shell
python evaluate_mvs.py
```
## Citation
If you find our work useful in your research, please consider citing our paper: