search

XingangPan / GAN2Shape

Code for GAN2Shape (ICLR2021 oral)
https://arxiv.org/abs/2011.00844
MIT License
575 stars 101 forks source link

How to get the view_mvn and light_mvn files of my datasets? #17

Open RainCoderJoe opened 3 years ago

RainCoderJoe commented 3 years ago

Hi. Thank you for your works! These view_light files only include car, celeba, face and cat. How can I get the view_mvn and light_mvn of my datasets?

XingangPan commented 3 years ago

@RainCoderJoe Hi, you can use the method in this repo https://github.com/elliottwu/unsup3d to estimate the mean and covariance of viewpoint and lighting variations.

RainCoderJoe commented 3 years ago

In other words, I need to train unsup3d on my datasets, and then estimate viewpoint and lighting of all images, and finally get the mean and covariance of viewpoint and lighting?

XingangPan commented 3 years ago

Yes, that's what I mean. Besides, you may also try using the provided view_mvn files and see if they work. Usually, the view_mvn does not have to be very accurate.

RainCoderJoe commented 3 years ago

Thank you for your help!