diff options
author | Niklas Haas <git@haasn.xyz> | 2017-06-27 01:05:43 +0200 |
---|---|---|
committer | Niklas Haas <git@haasn.xyz> | 2017-06-27 01:05:43 +0200 |
commit | db36aa06f479aa5374b961b05c295e24b9cca629 (patch) | |
tree | 90430da53d85a09722097a857fc3246b387c3a14 /DOCS/man/mpv.rst | |
parent | f82ba75bd457a139afddd8ca58f99dc2f270a0b2 (diff) | |
download | mpv-db36aa06f479aa5374b961b05c295e24b9cca629.tar.bz2 mpv-db36aa06f479aa5374b961b05c295e24b9cca629.tar.xz |
vo_opengl: tone map using only luminance information
This is even better at preventing discoloration than tone mapping on the
XYZ image. Partly inspired by the HLG OOTF. Also simplifies the way we
tone map, and moves this logic to the pass_tone_map function where it
belongs.
This also fixes what could arguably be considered a bug in the HLG
implementation when using HLG for non-BT.2020 colorspaces, which is not
permitted by spec but thinkable in theory. Although in this case, I
guess it will be arbitrary whether people use the BT.2020-normalized
luma coefficients or change it to fit the colorspace, so I guess either
way could be considered "right", depending on what people end up doing.
Either way, in lieue of standard practice, we do what makes the most
sense (to me), and hopefully others will follow.
The downside is that we upload an extra vec3 uniform even if we don't
use it, but eliminating that would be ugly.
Diffstat (limited to 'DOCS/man/mpv.rst')
0 files changed, 0 insertions, 0 deletions