Question about the coordinate system transformation

autonomousvision / giraffe

This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"

https://m-niemeyer.github.io/project-pages/giraffe/index.html

MIT License

1.23k stars 160 forks source link

Question about the coordinate system transformation #43

Closed LeoXing1996 closed 2 years ago

LeoXing1996 commented 2 years ago

Thanks for the great work! However, I still have a question about the coordinate system transformation.

https://github.com/autonomousvision/giraffe/blob/39da6b434b5c14893a35f009f04c05e43c1b2bc6/im2scene/giraffe/models/generator.py#L399-L402

In the above codes, you first generate the coordinates under the image coordinate system, then invert the y-axis. What is the purpose of this operation?

Looking forward to your reply.

m-niemeyer commented 2 years ago

This is how our coordinate system is defined: second axis goes from top to bottom as opposed to bottom to top. It is a common system when working with images!