meteorshowers / Stereonet Activestereonet
Licence: mit
stereo matching StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth prediction model in pytorch. ECCV2018; ActiveStereoNet:End-to-End Self-Supervised Learning for Active Stereo Systems ECCV2018 Oral
Stars: ✭ 308
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Stereonet Activestereonet
Ocbarrage
iOS 弹幕库 OCBarrage, 同时渲染5000条弹幕也不卡, 轻量, 可拓展, 高度自定义动画, 超高性能, 简单易上手; A barrage render-engine with high performance for iOS. At the same time, rendering 5000 barrages is also very smooth, lightweight, scalable, highly custom animation, ultra high performance, simple and easy to use!
Stars: ✭ 294 (-4.55%)
Mutual labels: google
Yjs
Shared data types for building collaborative software
Stars: ✭ 5,894 (+1813.64%)
Mutual labels: realtime
Translators
🌏🌍🌎Translators🌎🌍🌏 is a library which aims to bring free, multiple, enjoyable translation to individuals and students in Python. Translators是一个旨在用Python为个人和学生带来免费、多样、愉快翻译的库。
Stars: ✭ 295 (-4.22%)
Mutual labels: google
Ccat
Cloud Container Attack Tool (CCAT) is a tool for testing security of container environments.
Stars: ✭ 300 (-2.6%)
Mutual labels: google
Angelo
Sinatra-like DSL for Reel that supports WebSockets and SSE
Stars: ✭ 303 (-1.62%)
Mutual labels: realtime
Hacker Tab Extension
Browser extension to view GitHub trending projects on new tab 📈
Stars: ✭ 287 (-6.82%)
Mutual labels: google
Hybridauth
Open source social sign on PHP Library. HybridAuth goal is to act as an abstract api between your application and various social apis and identities providers such as Facebook, Twitter and Google.
Stars: ✭ 3,223 (+946.43%)
Mutual labels: google
Laravel Google Drive Demo
Laravel & Google Drive Storage - Demo project with Laravel 5.4
Stars: ✭ 299 (-2.92%)
Mutual labels: google
Realtime App
Deploy a serverless realtime app built on AWS Lambda using Serverless Components.
Stars: ✭ 299 (-2.92%)
Mutual labels: realtime
Awesome Privacy
A curated list of services and alternatives that respect your privacy because PRIVACY MATTERS.
Stars: ✭ 303 (-1.62%)
Mutual labels: google
Laravel Socialite
Social OAuth Authentication for Laravel 5. drivers: facebook, github, google, linkedin, weibo, qq, wechat and douban
Stars: ✭ 296 (-3.9%)
Mutual labels: google
Attention is all you need
Transformer of "Attention Is All You Need" (Vaswani et al. 2017) by Chainer.
Stars: ✭ 303 (-1.62%)
Mutual labels: google
Loopa News
Realtime social news app developed from scratch with Elixir, Phoenix, Vue and Vuex
Stars: ✭ 308 (+0%)
Mutual labels: realtime
Markserv
🏁 serve markdown as html (GitHub style), index directories, live-reload as you edit
Stars: ✭ 304 (-1.3%)
Mutual labels: realtime
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth prediction model in pytorch. ECCV2018
ActiveStereoNet:End-to-End Self-Supervised Learning for Active Stereo Systems ECCV2018 Oral
If you want to communicate with me about the StereoNet, please concact me without hesitating. My email:
[email protected]
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth prediction model in pytorch. ECCV2018
StereoNet Introduction
I implement the real-time stereo model according to the StereoNet model in pytorch.
| Method | EPE_all on sceneflow dataset | EPE_all on kitti2012 dataset | EPE_all on kitti2015 dataset |
|---|---|---|---|
| ours(8X single) | stage0:2.26 stage1:1.38 | ||
| Reference[1] | stage1: 1.525 |
my model result
Now, my model's speed can achieve 25 FPS on 540*960 img with the best result of 1.87 EPE_all with 16X multi model， 1.95 EPE_all with 16X single model on sceneflow dataset by end-to-end training. the following are the side outputs and the prediction example
train example
test example
real time version submission
- KITTI2015 submission: http://www.cvlibs.net/datasets/kitti/eval_scene_flow_detail.php?benchmark=stereo&result=19f20256af911773b2815a995644f237f229968e ranking 175
point cloud view example
ActiveStereoNet:End-to-End Self-Supervised Learning for Active Stereo Systems ECCV2018 Oral
ActiveStereoNet model disparity vis result
ActiveStereoNet model surface normal vis result
plane fit mertric result
ActiveStereoNet youtube video demo
- youtube video https://www.youtube.com/watch?v=pqKZs1b1b0Y.
Citation
- refercence[1]
If you find our work useful in your research, please consider citing:
@inproceedings{khamis2018stereonet, title={Stereonet: Guided hierarchical refinement for real-time edge-aware depth prediction}, author={Khamis, Sameh and Fanello, Sean and Rhemann, Christoph and Kowdle, Adarsh and Valentin, Julien and Izadi, Shahram}, booktitle={Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany}, pages={8--14}, year={2018} }
License
- Our code is released under MIT License (see LICENSE file for details).
Installaton
- python3.6
- pytorch0.4
Usage
- run main8Xmulti.py
Updates
- finetune the performance beating the original paper.
rethink
- Do not design massive deep networks with multiple stages to improve kitti by 1%(no meaning doing this)
- Use metrics that matter for visual navigation (hint: not L1 depth error)
- ...
pretrain model
StereoNet pretrain model(pytorch version)
- Sceneflow pretrain weight https://drive.google.com/open?id=1bSwewxrRfmFCxZDyAtyYyQQiw05nSFI8.
ActiveStereoNet pretrain model(pytorch version)
- D435 pretrain weight https://drive.google.com/file/d/1MDbRy4jO3IWM0zqn_D0sbZVjECZIl4g3/view?usp=sharing.
ActiveStereoNet pretrain model(tensorflow version)
- D435 pretrain weight https://drive.google.com/open?id=1bSwewxrRfmFCxZDyAtyYyQQiw05nSFI8.
Thanks
- Thanks to Sameh Khamis' help
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].