# IGEV-Stereo

**Repository Path**: ykuo/igev-stereo

## Basic Information

- **Project Name**: IGEV-Stereo
- **Description**: 复现先进算法：IGEV-Stereo
复现代码来源于开源代码：gangweiX/IGEV
复现论文：Iterative Geometry Encoding Volume for Stereo Matching
- **Primary Language**: Python
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2023-11-26
- **Last Updated**: 2025-08-16

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# IGEV-Stereo

#### 介绍

- 复现先进算法：IGEV-Stereo
- 复现代码来源于开源代码：[gangweiX/IGEV](https://github.com/gangweiX/IGEV)
- 复现论文：Iterative Geometry Encoding Volume for Stereo Matching

#### 软件架构

- python3.11
- pytorch2.1.0+cu121

#### 安装教程

1.  xxxx
2.  xxxx
3.  xxxx

#### 使用说明

1.  tensorboard --logdir=./checkpoints/* --port=6006
2.  watch -n 1 nvidia-smi
3.  netstat -ano | findstr :6006
4.  nohup python ./main.py > ./checkpoints/*/nohup.log 2>&1 &
5.  tail -f ./checkpoints/*/nohup.log
6.  ps aux|grep python

#####  训练Training
    # To train on KITTI, run
    python train_stereo.py --dataset kitti --image_size 352 1216 --batch_size 4
    # To train on USVInland, run
    python train_stereo.py --dataset usvinland --image_size 320 640 --max_disp 64 --batch_size 10
    # To train on Segmented USVInland, run
    python train_stereo.py --dataset usvinland_seg --image_size 320 640 --max_disp 64 --batch_size 10

#####  评估Evaluation
    # To evaluate on KITTI, run
    python evaluate_stereo.py --restore_ckpt ./save/kitti/kitti.pth --dataset kitti
    # To evaluate on USVInland, run
    python evaluate_stereo.py --restore_ckpt ./save/usvinland/usvinland.pth --dataset usvinland
    # To evaluate on Segmented USVInland, run
    python evaluate_stereo.py --restore_ckpt ./save/usvinland_seg/usvinland.pth --dataset usvinland_seg

#####  测试Test
    # To test on KITTI, run
    python evaluate_stereo.py --restore_ckpt ./save/kitti/kitti.pth --dataset kitti --mode test
    # To test on USVInland, run
    python evaluate_stereo.py --restore_ckpt ./save/usvinland/usvinland.pth --dataset usvinland --mode test
    # To test on Segmented USVInland, run
    python evaluate_stereo.py --restore_ckpt ./save/usvinland_seg/usvinland.pth --dataset usvinland_seg

#####  演示Demo
    # Input pth, default input demo-imgs, out demo-output, run
    python demo_imgs.py --restore_ckpt ./save/usvinland/usvinland.pth

#####  提交Submission
    # For submission to the KITTI benchmark, run
    python save_disp.py

#####  多视角MVS立体训练与评估
    # To train on DTU, run
    python train_mvs.py
    # To evaluate on DTU, run
    python evaluate_mvs.py

#### 参与贡献

1.  Fork 本仓库
2.  新建 Feat_xxx 分支
3.  提交代码
4.  新建 Pull Request

#### 特技

1.  使用 Readme\_XXX.md 来支持不同的语言，例如 Readme\_en.md, Readme\_zh.md
2.  Gitee 官方博客 [blog.gitee.com](https://blog.gitee.com)
3.  你可以 [https://gitee.com/explore](https://gitee.com/explore) 这个地址来了解 Gitee 上的优秀开源项目
4.  [GVP](https://gitee.com/gvp) 全称是 Gitee 最有价值开源项目，是综合评定出的优秀开源项目
5.  Gitee 官方提供的使用手册 [https://gitee.com/help](https://gitee.com/help)
6.  Gitee 封面人物是一档用来展示 Gitee 会员风采的栏目 [https://gitee.com/gitee-stars/](https://gitee.com/gitee-stars/)

#### 引用
> @inproceedings{xu2023iterative,
  title={Iterative Geometry Encoding Volume for Stereo Matching},
  author={Xu, Gangwei and Wang, Xianqi and Ding, Xiaohuan and Yang, Xin},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={21919--21928},
  year={2023}
}