项目作者: yihui-he

项目描述 :
Depth estimation with neural network, and learning on RGBD images
高级语言: HTML
项目地址: git://github.com/yihui-he/Estimated-Depth-Map-Helps-Image-Classification.git
创建时间: 2016-05-23T17:04:55Z
项目社区:https://github.com/yihui-he/Estimated-Depth-Map-Helps-Image-Classification

开源协议:MIT License

下载


Estimated Depth Map Helps Image Classification

GitHub - yihui-he/Estimated-Depth-Map-Helps-Image-Classification: Depth estimation with neural network, and learning on RGBD images

Estimated Depth Map Helps Image Classification

Untitled

Untitled 1

if you find our work helpful in your research, please consider citing:

  1. @article{estimated2017he,
  2. title={Estimated Depth Map Helps Image Classification},
  3. author={He, Yihui},
  4. journal={arXiv preprint arXiv:1709.07077},
  5. year={2017}
  6. }

how to test

  1. you can run tryhere.ipynb to test performance on RGBD and RGB images.
  2. you can do depth estimation in train/ folder

Approach

  1. train a mapping map RGB to depth
  2. convert cifar10 to images
  3. convert RGBD to cifar10 format
  4. train neural network on RGBD dataset

download

dcnf-fcspRGBD CIFAR-10

all dataset descriptionsa good one