fangget / packnet-sfm-pytorch Goto Github PK

I need a monodepth estimation to achieve at least 88% accuracy from 80 - 100m , may it possible for now ?

Hello:
Thanks for your excellent work!
But I am curious how much frame rate the model can reach after reducing the amount of parameters?

In PackResNetEncoder x = (input_image - 0.45) / 0.225 image norm? why i don't see it in the paper?　and more details　I　cannot find it from the paper.

你好，非常感谢你的分享
请问有关相机内参学习的相关代码具体在哪部分？

Hi, thanks for sharing your implementation!

I was just wondering, why is the velocity loss (in trainer.py) commented out? Is it that it doesn't seem to work as well as the paper claims yet?

https://github.com/TRI-ML/packnet-sfm

Hi, Thank you for code!

I could not see reconstruction code. Would you say&share steps for reconstruction (as we can see in the last part of the video)?

Thanks in advance

How do I train with my own dataset? Can I complete my training directly using the continuous monocular video I collected? I don't have radar, speed, etc., what specific training data does he need?