More than 3 years have passed since last update.

【Mono Depth】PackNet : velocityのsupervise

Posted at 2021-02-02

3D Packing for Self-Supervised Monocular Depth Estimation

![image.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/482094/9a60a014-347c-2a5f-cc55-4156672a422c.png)

新規性

![image.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/482094/25ccfec6-163d-7854-41ec-aa23d658c6c6.png) velocityのsupervise

結果

![image.png](https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/482094/03a0ed84-1861-0d11-490b-19c1fca12a29.png) velocityのsuperviseがあってもほとんど精度が変わらない

結論

・velocityをsuperviseしてもほとんど効果がない。pose estimationの精度が良いのか、Ground Truthのvelocityの精度が悪いのか

参考文献

3D Packing for Self-Supervised Monocular Depth Estimation https://arxiv.org/pdf/1905.02693.pdf

You get articles that match your needs
You can efficiently read back useful information
You can use dark theme

What you can do with signing up