-
Notifications
You must be signed in to change notification settings - Fork 28
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
GT data [understanding the max of range] #13
Comments
@ittim4 In this repo, HDR values are not processed into [0, 1] in the data reading phase, while you can think that the Tanh function used in Tanh_L1 loss function is designed for normalization. |
@ittim4 GT_linear = GT_aligned ^ gamma. Linear signal is not strictly related to the value of nits for display-referred data. |
Thank you @chxy95 ! Interesting to know that HDR values are not processed into [0 1] and I see that, in the context of this problem, Tanh function (in Tanh_L1 loss) can serve as a normalization and also in that sense, one need not know strict relation to nits of display referred data. Q1. Can you help understand what's the rational behind using 99th percentile of GT as "norm_perc" value in line 31? why not just take max i.e. 100th percentile? |
@ittim4 Q1: The parameters of the tone mapping algorithm are default provided by the organizor. You can also use 100th percentile as norm_perc value. |
In summary, when a loss is calculated, the range of |
@UdonDa The range of |
First of all, thanks for your comments in this thread regarding align ratio. Wanted to understand few more details. For e.g.: How to find out what is the maximum nits represented in GT data? Is there any information or metadata indicated where GT is graded for say 1000nits, etc? Essentially, trying to understand whats the relationship of uint16 number in GT file and the nits it might represent.
Current understanding is:: GT data is uint16 & gamma encoded and lets say if original range was [0 M], it is always scaled in a way that max of image content will be represented by 65535 where alignratio= 65535/M.
Current thought process to make sense of GT data:
would be great if you can share your insight in this regard.
The text was updated successfully, but these errors were encountered: