| Message ID | 20240617134141.224614-3-derek.buitenhuis@gmail.com |
|---|---|
| State | New |
| Headers | show |
| Series | Vision Pro Spatial Data | expand |
| Context | Check | Description |
|---|---|---|
| yinshiyou/make_loongarch64 | success | Make finished |
| yinshiyou/make_fate_loongarch64 | success | Make fate finished |
| andriy/make_x86 | success | Make finished |
| andriy/make_fate_x86 | success | Make fate finished |
On 6/17/2024 10:41 AM, Derek Buitenhuis wrote: > Based on what is in the files themselves, and what the API provides > to users. > > URLs: > * https://developer.apple.com/documentation/videotoolbox/kvtcompressionpropertykey_heroeye > * https://developer.apple.com/documentation/videotoolbox/kvtcompressionpropertykey_stereocamerabaseline > * https://developer.apple.com/documentation/videotoolbox/kvtcompressionpropertykey_horizontaldisparityadjustment > * https://developer.apple.com/documentation/coremedia/kcmformatdescriptionextension_horizontalfieldofview > > Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com> > --- > libavutil/stereo3d.c | 52 +++++++++++++++++++++++++++++ > libavutil/stereo3d.h | 78 ++++++++++++++++++++++++++++++++++++++++++++ > libavutil/version.h | 2 +- > 3 files changed, 131 insertions(+), 1 deletion(-) > > diff --git a/libavutil/stereo3d.c b/libavutil/stereo3d.c > index 9c29ab01b5..a40a9439bb 100644 > --- a/libavutil/stereo3d.c > +++ b/libavutil/stereo3d.c > @@ -55,6 +55,18 @@ static const char * const stereo3d_type_names[] = { > [AV_STEREO3D_COLUMNS] = "interleaved columns", > }; > > +static const char * const stereo3d_view_names[] = { > + [AV_STEREO3D_VIEW_PACKED] = "packed", > + [AV_STEREO3D_VIEW_LEFT] = "left", > + [AV_STEREO3D_VIEW_RIGHT] = "right", > +}; > + > +static const char * const stereo3d_primary_eye_names[] = { > + [AV_PRIMARY_EYE_NONE] = "none", > + [AV_PRIMARY_EYE_LEFT] = "left", > + [AV_PRIMARY_EYE_RIGHT] = "right", > +}; > + > const char *av_stereo3d_type_name(unsigned int type) > { > if (type >= FF_ARRAY_ELEMS(stereo3d_type_names)) > @@ -74,3 +86,43 @@ int av_stereo3d_from_name(const char *name) > > return -1; > } > + > +const char *av_stereo3d_view_name(unsigned int view) > +{ > + if (view >= FF_ARRAY_ELEMS(stereo3d_view_names)) > + return "unknown"; > + > + return stereo3d_view_names[view]; > +} > + > +int av_stereo3d_view_from_name(const char *name) > +{ > + int i; > + > + for (i = 0; i < FF_ARRAY_ELEMS(stereo3d_view_names); i++) { > + if (av_strstart(name, stereo3d_view_names[i], NULL)) > + return i; > + } > + > + return -1; > +} > + > +const char *av_stereo3d_primary_eye_name(unsigned int eye) > +{ > + if (eye >= FF_ARRAY_ELEMS(stereo3d_primary_eye_names)) > + return "unknown"; > + > + return stereo3d_primary_eye_names[eye]; > +} > + > +int av_stereo3d_primary_eye_from_name(const char *name) > +{ > + int i; > + > + for (i = 0; i < FF_ARRAY_ELEMS(stereo3d_primary_eye_names); i++) { > + if (av_strstart(name, stereo3d_primary_eye_names[i], NULL)) > + return i; > + } > + > + return -1; > +} > diff --git a/libavutil/stereo3d.h b/libavutil/stereo3d.h > index 3aab959b79..d35e46e670 100644 > --- a/libavutil/stereo3d.h > +++ b/libavutil/stereo3d.h > @@ -158,6 +158,26 @@ enum AVStereo3DView { > AV_STEREO3D_VIEW_RIGHT, > }; > > +/** > + * List of possible primary eyes. > + */ > +enum AVStereo3DPrimaryEye { > + /** > + * Neither eye. > + */ > + AV_PRIMARY_EYE_NONE, > + > + /** > + * Left eye. > + */ > + AV_PRIMARY_EYE_LEFT, > + > + /** > + * Right eye > + */ > + AV_PRIMARY_EYE_RIGHT, > +}; > + > /** > * Inverted views, Right/Bottom represents the left view. > */ > @@ -185,6 +205,28 @@ typedef struct AVStereo3D { > * Determines which views are packed. > */ > enum AVStereo3DView view; > + > + /** > + * Which eye is the primary eye when rendering in 2D. > + */ > + enum AVStereo3DPrimaryEye primary_eye; > + > + /** > + * The distance between the centres of the lenses of the camera system, > + * in micrometers. Zero if unset. > + */ > + uint32_t baseline; > + > + /** > + * Relative shift of the left and right images, which changes the zero parallax plane. > + * Range -10000 to 10000, mapped to -1.0 to 1.0. Zero if unset. Maybe this should be an AVRational then. > + */ > + int32_t horizontal_disparity_adjustment; > + > + /** > + * Horizontal field of view in thousanths of a degree. Zero if unset. > + */ > + uint32_t horizontal_field_of_view; > } AVStereo3D; > > /** > @@ -222,6 +264,42 @@ const char *av_stereo3d_type_name(unsigned int type); > */ > int av_stereo3d_from_name(const char *name); > > +/** > + * Provide a human-readable name of a given stereo3d view. > + * > + * @param type The input stereo3d view value. > + * > + * @return The name of the stereo3d view value, or "unknown". > + */ > +const char *av_stereo3d_view_name(unsigned int view); > + > +/** > + * Get the AVStereo3DView form a human-readable name. > + * > + * @param name The input string. > + * > + * @return The AVStereo3DView value, or -1 if not found. > + */ > +int av_stereo3d_view_from_name(const char *name); > + > +/** > + * Provide a human-readable name of a given stereo3d primary eye. > + * > + * @param type The input stereo3d primary eye value. > + * > + * @return The name of the stereo3d primary eye value, or "unknown". > + */ > +const char *av_stereo3d_primary_eye_name(unsigned int eye); > + > +/** > + * Get the AVStereo3DPrimaryEye form a human-readable name. > + * > + * @param name The input string. > + * > + * @return The AVStereo3DPrimaryEye value, or -1 if not found. > + */ > +int av_stereo3d_primary_eye_from_name(const char *name); > + > /** > * @} > */ > diff --git a/libavutil/version.h b/libavutil/version.h > index 7df546ee22..8044fd3935 100644 > --- a/libavutil/version.h > +++ b/libavutil/version.h > @@ -79,7 +79,7 @@ > */ > > #define LIBAVUTIL_VERSION_MAJOR 59 > -#define LIBAVUTIL_VERSION_MINOR 23 > +#define LIBAVUTIL_VERSION_MINOR 24 > #define LIBAVUTIL_VERSION_MICRO 100 > > #define LIBAVUTIL_VERSION_INT AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \
On 6/17/2024 5:53 PM, James Almer wrote:
> Maybe this should be an AVRational then.
While that is probably 'more correct', it does mean that in 100% places
this could be used, it'll have to be converted back to the -10000 to 10000
range. Is there a simple way to do that with an AVRational that doesn't
involve a round trip to a double or float (i.e. lossy)?
- Derek
On 6/17/2024 2:07 PM, Derek Buitenhuis wrote: > On 6/17/2024 5:53 PM, James Almer wrote: >> Maybe this should be an AVRational then. > > While that is probably 'more correct', it does mean that in 100% places > this could be used, it'll have to be converted back to the -10000 to 10000 > range. Is there a simple way to do that with an AVRational that doesn't > involve a round trip to a double or float (i.e. lossy)? No, it's av_d2q(), av_q2d(), and av_rescale() as needed. Same as we do for Mastering Display and Ambient Viewing Environment Metadata. The reason to use AVRational is that in this specific spec the values have a denominator of 10000, but in others it doesn't need to, allowing for more precise values (Matroska would store it as a double, in fact). So we shouldn't define our API for one specific implementation but rather in a generic way that should accommodate to any potential implementation. I think we already did the former with a Google implementation (x.y fixed point values), and i want to avoid doing it again. > > - Derek > _______________________________________________ > ffmpeg-devel mailing list > ffmpeg-devel@ffmpeg.org > https://ffmpeg.org/mailman/listinfo/ffmpeg-devel > > To unsubscribe, visit link above, or email > ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".
On 6/17/2024 7:09 PM, James Almer wrote: > No, it's av_d2q(), av_q2d(), and av_rescale() as needed. Same as we do > for Mastering Display and Ambient Viewing Environment Metadata. > The reason to use AVRational is that in this specific spec the values > have a denominator of 10000, but in others it doesn't need to, allowing > for more precise values (Matroska would store it as a double, in fact). This is unfortunate. Possibly we should add some util func for this case, as it's a case I know I've personally hit more than once (with bugs caused by lossy roundtrip) in my own code - I ended up manually using num/den in the end. > So we shouldn't define our API for one specific implementation but > rather in a generic way that should accommodate to any potential > implementation. I think we already did the former with a Google > implementation (x.y fixed point values), and i want to avoid doing it again. Will send a v3 set using AVRational, then. - Derek
diff --git a/libavutil/stereo3d.c b/libavutil/stereo3d.c index 9c29ab01b5..a40a9439bb 100644 --- a/libavutil/stereo3d.c +++ b/libavutil/stereo3d.c @@ -55,6 +55,18 @@ static const char * const stereo3d_type_names[] = { [AV_STEREO3D_COLUMNS] = "interleaved columns", }; +static const char * const stereo3d_view_names[] = { + [AV_STEREO3D_VIEW_PACKED] = "packed", + [AV_STEREO3D_VIEW_LEFT] = "left", + [AV_STEREO3D_VIEW_RIGHT] = "right", +}; + +static const char * const stereo3d_primary_eye_names[] = { + [AV_PRIMARY_EYE_NONE] = "none", + [AV_PRIMARY_EYE_LEFT] = "left", + [AV_PRIMARY_EYE_RIGHT] = "right", +}; + const char *av_stereo3d_type_name(unsigned int type) { if (type >= FF_ARRAY_ELEMS(stereo3d_type_names)) @@ -74,3 +86,43 @@ int av_stereo3d_from_name(const char *name) return -1; } + +const char *av_stereo3d_view_name(unsigned int view) +{ + if (view >= FF_ARRAY_ELEMS(stereo3d_view_names)) + return "unknown"; + + return stereo3d_view_names[view]; +} + +int av_stereo3d_view_from_name(const char *name) +{ + int i; + + for (i = 0; i < FF_ARRAY_ELEMS(stereo3d_view_names); i++) { + if (av_strstart(name, stereo3d_view_names[i], NULL)) + return i; + } + + return -1; +} + +const char *av_stereo3d_primary_eye_name(unsigned int eye) +{ + if (eye >= FF_ARRAY_ELEMS(stereo3d_primary_eye_names)) + return "unknown"; + + return stereo3d_primary_eye_names[eye]; +} + +int av_stereo3d_primary_eye_from_name(const char *name) +{ + int i; + + for (i = 0; i < FF_ARRAY_ELEMS(stereo3d_primary_eye_names); i++) { + if (av_strstart(name, stereo3d_primary_eye_names[i], NULL)) + return i; + } + + return -1; +} diff --git a/libavutil/stereo3d.h b/libavutil/stereo3d.h index 3aab959b79..d35e46e670 100644 --- a/libavutil/stereo3d.h +++ b/libavutil/stereo3d.h @@ -158,6 +158,26 @@ enum AVStereo3DView { AV_STEREO3D_VIEW_RIGHT, }; +/** + * List of possible primary eyes. + */ +enum AVStereo3DPrimaryEye { + /** + * Neither eye. + */ + AV_PRIMARY_EYE_NONE, + + /** + * Left eye. + */ + AV_PRIMARY_EYE_LEFT, + + /** + * Right eye + */ + AV_PRIMARY_EYE_RIGHT, +}; + /** * Inverted views, Right/Bottom represents the left view. */ @@ -185,6 +205,28 @@ typedef struct AVStereo3D { * Determines which views are packed. */ enum AVStereo3DView view; + + /** + * Which eye is the primary eye when rendering in 2D. + */ + enum AVStereo3DPrimaryEye primary_eye; + + /** + * The distance between the centres of the lenses of the camera system, + * in micrometers. Zero if unset. + */ + uint32_t baseline; + + /** + * Relative shift of the left and right images, which changes the zero parallax plane. + * Range -10000 to 10000, mapped to -1.0 to 1.0. Zero if unset. + */ + int32_t horizontal_disparity_adjustment; + + /** + * Horizontal field of view in thousanths of a degree. Zero if unset. + */ + uint32_t horizontal_field_of_view; } AVStereo3D; /** @@ -222,6 +264,42 @@ const char *av_stereo3d_type_name(unsigned int type); */ int av_stereo3d_from_name(const char *name); +/** + * Provide a human-readable name of a given stereo3d view. + * + * @param type The input stereo3d view value. + * + * @return The name of the stereo3d view value, or "unknown". + */ +const char *av_stereo3d_view_name(unsigned int view); + +/** + * Get the AVStereo3DView form a human-readable name. + * + * @param name The input string. + * + * @return The AVStereo3DView value, or -1 if not found. + */ +int av_stereo3d_view_from_name(const char *name); + +/** + * Provide a human-readable name of a given stereo3d primary eye. + * + * @param type The input stereo3d primary eye value. + * + * @return The name of the stereo3d primary eye value, or "unknown". + */ +const char *av_stereo3d_primary_eye_name(unsigned int eye); + +/** + * Get the AVStereo3DPrimaryEye form a human-readable name. + * + * @param name The input string. + * + * @return The AVStereo3DPrimaryEye value, or -1 if not found. + */ +int av_stereo3d_primary_eye_from_name(const char *name); + /** * @} */ diff --git a/libavutil/version.h b/libavutil/version.h index 7df546ee22..8044fd3935 100644 --- a/libavutil/version.h +++ b/libavutil/version.h @@ -79,7 +79,7 @@ */ #define LIBAVUTIL_VERSION_MAJOR 59 -#define LIBAVUTIL_VERSION_MINOR 23 +#define LIBAVUTIL_VERSION_MINOR 24 #define LIBAVUTIL_VERSION_MICRO 100 #define LIBAVUTIL_VERSION_INT AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \
Based on what is in the files themselves, and what the API provides to users. URLs: * https://developer.apple.com/documentation/videotoolbox/kvtcompressionpropertykey_heroeye * https://developer.apple.com/documentation/videotoolbox/kvtcompressionpropertykey_stereocamerabaseline * https://developer.apple.com/documentation/videotoolbox/kvtcompressionpropertykey_horizontaldisparityadjustment * https://developer.apple.com/documentation/coremedia/kcmformatdescriptionextension_horizontalfieldofview Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com> --- libavutil/stereo3d.c | 52 +++++++++++++++++++++++++++++ libavutil/stereo3d.h | 78 ++++++++++++++++++++++++++++++++++++++++++++ libavutil/version.h | 2 +- 3 files changed, 131 insertions(+), 1 deletion(-)