Re: MMX speedup for Floyd Steinberg error diffusion

rep_movsd wrote:
>> Phil, you're absolutely right, and that's why "doing it right" is even
>> harder than you're showing here:
> 
> There is this color quantizer/ditherer program called scolorq which
> uses some highly advanced techniques with floating point precision. I

I.e. convert each pixel to fp, then to a linear color space, do all 
error diffusion in this format, then use the final palette colors?

> tried that out and it took an astoni****ng amount of time for a single
> frame ( I let it run for 3 minutes before giving up in disgust ).
> Turns out it has 5 deep nested loops. Some site online shows pretty
> impressive results for reduction to 16 color images. Perhaps the

You might be able to do 16-color images by making the color diffusion 
are significantly larger: Keep luminance info as close as possible, but 
allow color to be spread across a larger area?

> BTW This whole thing could be avoided if browser vendors implemented
> GIF decoding exactly according to the standard. Then it would be
> possible to have animations where a number of frames are rendered
> instantaneously (with 0 frame duration) and we could have true true-
> color GIFs.

Huh?

I guess you intend that each frame should be visible a fraction of a 
second, otherwise it cannot take part in the visual center averaging,
right?

The problem with this idea is that color displays are digital devices, 
with a granularity of 60/70/80 Hz, or whatever your refresh rate happens 
to be. Writing two images between frame updates wil simply lose the 
first one. :-(

Terje

-- 
- <Terje.Mathisen@[EMAIL PROTECTED]
>
"almost all programming can be viewed as an exercise in caching"