Coder Social home page Coder Social logo

jackyfriend / ad-depth-estimation Goto Github PK

View Code? Open in Web Editor NEW

This project forked from bei181/ad-depth-estimation

0.0 0.0 0.0 194.59 MB

License: MIT License

Shell 0.68% C++ 0.35% Python 77.16% C 0.10% MATLAB 0.60% Cuda 0.53% Jupyter Notebook 20.57% Starlark 0.01%

ad-depth-estimation's Introduction

AD-Depth-Estimation

代码

  1. traditional depth estimation 包含sfm和sfs两种传统方法,对应深度估计课程实战课中的传统实战方法

  2. 基于连续帧的自监督学习方法: monodepth2 和 FeatDepth

  3. 处理动态物体的自监督学习方法: depth and motion learning 和 struct2depth

  4. depth_estimate_application:是深度估计应用的一些代码,包括尺度恢复,伪点云生成,以及真实尺度下RGBD可视化

数据集

  1. sfm所用数据集存放在百度网盘: https://pan.baidu.com/s/1bQpqF4Zn6O4C1WNfKNjcmQ 提取码: z682;

  2. sfs数据集存放在sfs代码中的res文件夹中

  3. kitti数据集可以从官网下载: http://www.cvlibs.net/datasets/kitti/raw_data.php

也可以从百度网盘下载: https://pan.baidu.com/s/1qdoGlaRq8q-d0_bsAbrvyg 提取码: lu95

  1. cityscapes数据集官网下载链接: https://www.cityscapes-dataset.com/

  2. 私有数据集存放在百度网盘链接 链接: https://pan.baidu.com/s/1OFeCMCj8d2vAtNelgeGdGQ 提取码: 1nwa (文件较大,split命令行分割成多个包)

预训练模型

  1. depth_and_motion 在 kitti 和 cityscapes 上训练的模型

  2. tensorflow 格式的 resnet 18 预训练权重

  3. struct2depth 在 kitti 和 cityscapes 上训练的模型

都存放在百度网盘: https://pan.baidu.com/s/18oFEx5u8x_qwL7xXHAJyhg 提取码: 7kto

如果上述链接失效,可以查看如下链接: https://pan.baidu.com/s/1FnkXgAueeLeI-QgALE-MmA 提取码:2333

ad-depth-estimation's People

Contributors

aaronswei avatar bei181 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.