Jump to content

  • Log In with Google      Sign In   
  • Create Account

help on hdr rendering


Old topic!

Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.


  • You cannot reply to this topic
5 replies to this topic

#1   Members   -  Reputation: 509

Like
0Likes
Like

Posted 05 April 2014 - 05:50 AM

Hello .
Let's say I have my light buffer in hdr and now I want to tonemap it to ldr . my question is why everyone are doing downscale for multiple times to get a 1x1 texture to get average luminance ?
let's say this is the average luminance formula :
(1/N)*(total of the sum of log luminances off all pixels)
where N is the total pixel numbers . even I have seen people use compute shaders for downscaling. Isn't it just possible to write a compute shader that goes over all pixels and sum all of log luminances and put it in a float . then simply we can multiply this float value by 1/N either by cpu or gpu ?

#2   Crossbones+   -  Reputation: 4359

Like
3Likes
Like

Posted 05 April 2014 - 05:59 AM

Thats exactly what downscaling does, sums the pixel values in parallel.

 

Every thread can sum a small amount of pixels so you can have multiple threads. It wouldnt be so fast if you had a single thread go through every pixel and sum them up sequentially.

 

I guess you can change the amount of pixels each thread processes (eg instead of 2x2 -> 1 pixel you could have 4x4 -> 1 pixel but i dont know how that would work out)


o3o


#3   Members   -  Reputation: 769

Like
3Likes
Like

Posted 05 April 2014 - 06:23 AM

Isn't it just possible to write a compute shader that goes over all pixels and sum all of log luminances and put it in a float . then simply we can multiply this float value by 1/N either by cpu or gpu ?

 

This can be done by using Parallel Reduction algorithm:

http://developer.download.nvidia.com/compute/cuda/1.1-Beta/x86_website/projects/reduction/doc/reduction.pdf



#4   Crossbones+   -  Reputation: 13030

Like
3Likes
Like

Posted 05 April 2014 - 06:26 AM

 

Isn't it just possible to write a compute shader that goes over all pixels and sum all of log luminances and put it in a float . then simply we can multiply this float value by 1/N either by cpu or gpu ?

 

This can be done by using Parallel Reduction algorithm:

http://developer.download.nvidia.com/compute/cuda/1.1-Beta/x86_website/projects/reduction/doc/reduction.pdf

 

 

Which basically amounts to downsampling in the case of a 2D buffer smile.png


“If I understand the standard right it is legal and safe to do this but the resulting value could be anything.”


#5   Members   -  Reputation: 769

Like
0Likes
Like

Posted 05 April 2014 - 07:13 AM

 

 

Isn't it just possible to write a compute shader that goes over all pixels and sum all of log luminances and put it in a float . then simply we can multiply this float value by 1/N either by cpu or gpu ?

 

This can be done by using Parallel Reduction algorithm:

http://developer.download.nvidia.com/compute/cuda/1.1-Beta/x86_website/projects/reduction/doc/reduction.pdf

 

 

Which basically amounts to downsampling in the case of a 2D buffer smile.png

 

 

You can store your 2D buffer as 1D contiguous buffer with width*height elements and apply the Parallel reduction algorithm.



#6   Moderators   -  Reputation: 17898

Like
3Likes
Like

Posted 05 April 2014 - 12:39 PM

 

 

Isn't it just possible to write a compute shader that goes over all pixels and sum all of log luminances and put it in a float . then simply we can multiply this float value by 1/N either by cpu or gpu ?

 

This can be done by using Parallel Reduction algorithm:

http://developer.download.nvidia.com/compute/cuda/1.1-Beta/x86_website/projects/reduction/doc/reduction.pdf

 

 

Which basically amounts to downsampling in the case of a 2D buffer smile.png

 

 

Same end result, but you may be able to do it faster with a well-written reduction.






Old topic!

Guest, the last post of this topic is over 60 days old and at this point you may not reply in this topic. If you wish to continue this conversation start a new topic.




PARTNERS