GitLab

This becomes part of the picture properties, since users may want to
apply film grain themselves (e.g. for a GPU implementation).

The spec subtracts the signed offset from all of these when using them,
like it does for e.g. ar_coeffs_y_plus_128, although for some reason
the naming scheme is inconsistent here. Either way, it makes more sense
to treat them as signed integers than unsigned integers.

To avoid confusion since the name of the field is the same as the one in
the spec, we mark the type as int8_t (resp. int16_t for the 9-bit field)
to make it clear to the user that these are already signed integers.

Fixes #172.

Take the maximal number of tile rows and columns (each 64) into account.
Reduces size of Av1FrameHeader from 9588 to 1648 bytes on x86_64
according to pahole.
Refs #156.

Working only for the first Operating Point for now.

With minor contributions from:
 - Jean-Baptiste Kempf <jb@videolan.org>
 - Marvin Scholz <epirat07@gmail.com>
 - Hugo Beauzée-Luyssen <hugo@videolan.org>