fnzhan / EMLight

[AAAI 2021] EMLight: Lighting Estimation via Spherical Distribution Approximation, [TIP] GMLight: Lighting Estimation via Geometric Distribution Approximation
168 stars 35 forks source link

about supplementary file & daatset file structure #25

Closed liuyuwan233 closed 1 year ago

liuyuwan233 commented 1 year ago

Hi!

  1. In the paper, you mentioned 'Detailed network structure of neural projector and the training settings are provided in the supplementary file.', but I can not fild the supplementary file. Would you like to tell me where is the supplementary file?

  2. What's more, I tried to train my own dataset with your code for comparison, but I don't know the original file structure so I got some problems. Could you tell me the structure of the original file and the format of the images in the folder?

Thank you very much!

jxl0131 commented 1 year ago

Hi!

1. In the paper, you mentioned 'Detailed network structure of neural projector and the training settings are provided in the supplementary file.', but I can not fild the supplementary file. Would you like to tell me where is the supplementary file?

2. What's more, I tried to train my own dataset with your code for comparison, but I don't know the original file structure so I got some problems. Could you tell me the structure of the original file and the format of the images in the folder?

Thank you very much!

Hi!

I want follow EMLight's work, but i can't use LavalInDoor dataset, because professor Jean-François Lalonde told me that their server was broke down since bout 2 months ago. I wonder that what other dataset you want to use to train?

Thanks!

liuyuwan233 commented 1 year ago

Hi!

1. In the paper, you mentioned 'Detailed network structure of neural projector and the training settings are provided in the supplementary file.', but I can not fild the supplementary file. Would you like to tell me where is the supplementary file?

2. What's more, I tried to train my own dataset with your code for comparison, but I don't know the original file structure so I got some problems. Could you tell me the structure of the original file and the format of the images in the folder?

Thank you very much!

Hi!

I want follow EMLight's work, but i can't use LavalInDoor dataset, because professor Jean-François Lalonde told me that their server was broke down since bout 2 months ago. I wonder that what other dataset you want to use to train?

Thanks!

Hi! I wanted to train my own dataset to compare with EMLight's work, but I got some problems about the input file structure in the training and testing stage. And I have not solve these problems now...

jxl0131 commented 1 year ago

Hi!

1. In the paper, you mentioned 'Detailed network structure of neural projector and the training settings are provided in the supplementary file.', but I can not fild the supplementary file. Would you like to tell me where is the supplementary file?

2. What's more, I tried to train my own dataset with your code for comparison, but I don't know the original file structure so I got some problems. Could you tell me the structure of the original file and the format of the images in the folder?

Thank you very much!

Hi! I want follow EMLight's work, but i can't use LavalInDoor dataset, because professor Jean-François Lalonde told me that their server was broke down since bout 2 months ago. I wonder that what other dataset you want to use to train? Thanks!

Hi! I wanted to train my own dataset to compare with EMLight's work, but I got some problems about the input file structure in the training and testing stage. And I have not solve these problems now...

Hi!

You seem to be a chinese student, so am i. I know something about the input file structure, can i get your wechat? I have put my email on my profile.

Thanks!

fnzhan commented 1 year ago

For data structure, https://github.com/fnzhan/EMLight/blob/025f83dfb528d9211c45050237b9100647e7e622/RegressionNetwork/data.py#L23

crop_dir is the folder of cropped hdr images of a local region. gt_dir is the processed ground truth with distribution_representation.py in /RegressionNetwork/representation