https://github.com/jiarenchang/realtimestereo

Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)
https://github.com/jiarenchang/realtimestereo

psmnet pytorch real-time stereo-matching stereo-vision

Last synced: 2 months ago
JSON representation

Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)

• Host: GitHub
• URL: https://github.com/jiarenchang/realtimestereo
• Owner: JiaRenChang
• License: gpl-3.0
• Created: 2020-09-26T03:37:15.000Z (over 4 years ago)
• Default Branch: master
• Last Pushed: 2022-05-19T09:08:19.000Z (over 2 years ago)
• Last Synced: 2023-11-07T18:17:08.334Z (about 1 year ago)
• Topics: psmnet, pytorch, real-time, stereo-matching, stereo-vision
• Language: Python
• Homepage:
• Size: 85 KB
• Stars: 139
• Watchers: 5
• Forks: 26
• Open Issues: 10
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices

This repository contains the code (in PyTorch) for "[Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices](https://openaccess.thecvf.com/content/ACCV2020/papers/Chang_Attention-Aware_Feature_Aggregation_for_Real-time_Stereo_Matching_on_Edge_Devices_ACCV_2020_paper.pdf)" paper (ACCV 2020) by [Jia-Ren Chang](https://jiarenchang.github.io/), [Pei-Chun Chang](https://scholar.google.com/citations?user=eJUcMrQAAAAJ&hl=zh-TW) and [Yong-Sheng Chen](https://people.cs.nctu.edu.tw/~yschen/).

The codes mainly bring from [PSMNet](https://github.com/JiaRenChang/PSMNet/).

### Citation

```

@InProceedings{Chang_2020_ACCV,

    author    = {Chang, Jia-Ren and Chang, Pei-Chun and Chen, Yong-Sheng},

    title     = {Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices},

    booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)},

    month     = {November},

    year      = {2020}

}

```

### Train

As an example, use the following command to train a RTStereo on Scene Flow

```

python main.py --maxdisp 192 \

               --model RTStereoNet \

               --datapath (your scene flow data folder)\

               --epochs 10 \

               --loadmodel (optional)\

               --savemodel (path for saving model)

```

### Pretrained Model

KITTI 2015 Pretrained Model [Google Drive](https://drive.google.com/file/d/12EQKjntE_Vi6m9vpSzJRtuzDCRJRmYoV/view?usp=sharing)