0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 3 years have passed since last update.

【StereoDepth】stereo vs mono どっちが精度が良いのか?

Last updated at Posted at 2020-10-18

On the Importance of Stereo for Accurate Depth Estimation:An Efficient Semi-Supervised Deep Neural Network Approach

image.png

NVIDIAさんのリサーチでstereo depth estimationとmono depth estimationのどっちの方が精度が良いのか調べたら、stereoの方が良かったのでmonoは諦めて、stereoのalgorithmの紹介をしますという論文だった。

今回の寄与は
・Unspervised => Unspervised(Image)+Supervised(LiDAR)
特に新しい事では無いが、LiDARとImageの両方をLossに使えば精度が上がる。

・ReLU+Bachnorm => ELU
BatchNormをなくす事でネットワークが早く学習出来るようになったらしい。
*詳細はELUの論文に記載があった。

・soft-agmax => machine-learned-argmax
意思決定を行う前に、ネットワークがコンテキストをより適切に組み込むことができる

結果

![image.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/482094/238287ba-3b26-9cc7-949e-294fe3e2d1c7.png) 精度はまあまあ良いが、凄みがあるわけでもない

結論

monoよりstereoの方が精度が良い。 machine-learned-argmaxを使うことによって精度がどうなるか実験してみたい。

参考文献

On the Importance of Stereo for Accurate Depth Estimation:An Efficient Semi-Supervised Deep Neural Network Approach https://arxiv.org/pdf/1803.09719.pdf
0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?