fnzhan/EMLight

The input parameters for training of the Neural Projector of EMLight

Lingstreasure opened this issue · 3 comments

Hi fnzhan:
Could you please tell me which illumination map parameters you used as input during the training of the Neural Projector of EMlight, the parameters predicted by Regression network or the parameters of Ground Truth ?

hi,do you find the regression network ,the same image envalation model ,but output is different.as where, the first cov2 of network output is yet different!

We start with the Ground Truth, then turn to the predicted results.

We start with the Ground Truth, then turn to the predicted results.

Thanks for your reply. Thank you.