[FFmpeg-devel] [PATCH 1/3] lavu/pixfmt: Add P012, Y212, Y410, and Y412 formats
Philip Langdale
philipl at overt.org
Tue Aug 16 08:02:54 EEST 2022
These are the formats returned by the Intel VAAPI decoder for 12bit
4:2:0, 12bit 4:2:2, 10bit 4:4:4, and 12bit 4:4:4 respectively.
As with the already supported Y210 and YUVA (AVUY) formats, they are
based on formats Microsoft picked as their preferred 4:2:2 and 4:4:4
video formats, and Intel ran with it.
P12 and Y212 are simply an extension of 10 bit formats to say 12 bits
will be used, and Y412 is a normal looking packed 4 channel format
where the 12 most significant bits are used. Y410 is an annoying format
that packs three 10bit channels into 32bits with 2bits of alpha.
As a result, I had to define Y410 as a bitstream format, even though
each pixel is byte-aligned. If it is in-fact possible to define as a
normal byte-aligned format, please let me know how.
As with VUYA, I have kept the formal definition of Y410 and Y412 as
formats with alpha channels to maintain fidelity. The Intel folks say
they prefer this and they would rather explicitly use a format defined
as not having alpha than to silently drop it. The hardware decoder
does at least ensure the alpha channel is set to full opacity.
Signed-off-by: Philip Langdale <philipl at overt.org>
---
libavutil/pixdesc.c | 101 ++++++++++++++++++++++++++++++-
libavutil/pixfmt.h | 16 +++++
tests/ref/fate/imgutils | 8 +++
tests/ref/fate/sws-pixdesc-query | 42 +++++++++++++
4 files changed, 166 insertions(+), 1 deletion(-)
diff --git a/libavutil/pixdesc.c b/libavutil/pixdesc.c
index f7558ff8b9..0801927838 100644
--- a/libavutil/pixdesc.c
+++ b/libavutil/pixdesc.c
@@ -2147,6 +2147,30 @@ static const AVPixFmtDescriptor av_pix_fmt_descriptors[AV_PIX_FMT_NB] = {
},
.flags = AV_PIX_FMT_FLAG_PLANAR | AV_PIX_FMT_FLAG_BE,
},
+ [AV_PIX_FMT_P012LE] = {
+ .name = "p012le",
+ .nb_components = 3,
+ .log2_chroma_w = 1,
+ .log2_chroma_h = 1,
+ .comp = {
+ { 0, 2, 0, 4, 12 }, /* Y */
+ { 1, 4, 0, 4, 12 }, /* U */
+ { 1, 4, 2, 4, 12 }, /* V */
+ },
+ .flags = AV_PIX_FMT_FLAG_PLANAR,
+ },
+ [AV_PIX_FMT_P012BE] = {
+ .name = "p012be",
+ .nb_components = 3,
+ .log2_chroma_w = 1,
+ .log2_chroma_h = 1,
+ .comp = {
+ { 0, 2, 0, 4, 12 }, /* Y */
+ { 1, 4, 0, 4, 12 }, /* U */
+ { 1, 4, 2, 4, 12 }, /* V */
+ },
+ .flags = AV_PIX_FMT_FLAG_PLANAR | AV_PIX_FMT_FLAG_BE,
+ },
[AV_PIX_FMT_P016LE] = {
.name = "p016le",
.nb_components = 3,
@@ -2532,6 +2556,81 @@ static const AVPixFmtDescriptor av_pix_fmt_descriptors[AV_PIX_FMT_NB] = {
.flags = AV_PIX_FMT_FLAG_RGB | AV_PIX_FMT_FLAG_ALPHA |
AV_PIX_FMT_FLAG_FLOAT,
},
+ [AV_PIX_FMT_Y212LE] = {
+ .name = "y212le",
+ .nb_components = 3,
+ .log2_chroma_w = 1,
+ .log2_chroma_h = 0,
+ .comp = {
+ { 0, 4, 0, 4, 12 }, /* Y */
+ { 0, 8, 2, 4, 12 }, /* U */
+ { 0, 8, 6, 4, 12 }, /* V */
+ },
+ },
+ [AV_PIX_FMT_Y212BE] = {
+ .name = "y212be",
+ .nb_components = 3,
+ .log2_chroma_w = 1,
+ .log2_chroma_h = 0,
+ .comp = {
+ { 0, 4, 0, 4, 12 }, /* Y */
+ { 0, 8, 2, 4, 12 }, /* U */
+ { 0, 8, 6, 4, 12 }, /* V */
+ },
+ .flags = AV_PIX_FMT_FLAG_BE,
+ },
+ [AV_PIX_FMT_Y410LE] = {
+ .name = "y410le",
+ .nb_components= 4,
+ .log2_chroma_w= 0,
+ .log2_chroma_h= 0,
+ .comp = {
+ { 0, 32, 10, 0, 10 }, /* Y */
+ { 0, 32, 0, 0, 10 }, /* U */
+ { 0, 32, 20, 0, 10 }, /* V */
+ { 0, 32, 30, 0, 2 }, /* A */
+ },
+ .flags = AV_PIX_FMT_FLAG_ALPHA | AV_PIX_FMT_FLAG_BITSTREAM,
+ },
+ [AV_PIX_FMT_Y410BE] = {
+ .name = "y410be",
+ .nb_components= 4,
+ .log2_chroma_w= 0,
+ .log2_chroma_h= 0,
+ .comp = {
+ { 0, 32, 10, 0, 10 }, /* Y */
+ { 0, 32, 0, 0, 10 }, /* U */
+ { 0, 32, 20, 0, 10 }, /* V */
+ { 0, 32, 30, 0, 2 }, /* A */
+ },
+ .flags = AV_PIX_FMT_FLAG_BE | AV_PIX_FMT_FLAG_ALPHA | AV_PIX_FMT_FLAG_BITSTREAM,
+ },
+ [AV_PIX_FMT_Y412LE] = {
+ .name = "y412le",
+ .nb_components= 4,
+ .log2_chroma_w= 0,
+ .log2_chroma_h= 0,
+ .comp = {
+ { 0, 8, 2, 4, 12 }, /* Y */
+ { 0, 8, 0, 4, 12 }, /* U */
+ { 0, 8, 4, 4, 12 }, /* V */
+ { 0, 8, 6, 4, 12 }, /* A */
+ },
+ .flags = AV_PIX_FMT_FLAG_ALPHA,
+ },
+ [AV_PIX_FMT_Y412BE] = {
+ .name = "y412be",
+ .nb_components= 4,
+ .log2_chroma_w= 0,
+ .log2_chroma_h= 0,
+ .comp = {
+ { 0, 8, 2, 4, 12 }, /* Y */
+ { 0, 8, 0, 4, 12 }, /* U */
+ { 0, 8, 4, 4, 12 }, /* V */
+ { 0, 8, 6, 4, 12 }, /* A */
+ },
+ .flags = AV_PIX_FMT_FLAG_BE | AV_PIX_FMT_FLAG_ALPHA,
+ },
};
static const char * const color_range_names[] = {
@@ -2767,7 +2866,7 @@ void ff_check_pixfmt_descriptors(void){
if (!d->name && !d->nb_components && !d->log2_chroma_w && !d->log2_chroma_h && !d->flags)
continue;
-// av_log(NULL, AV_LOG_DEBUG, "Checking: %s\n", d->name);
+ av_log(NULL, AV_LOG_INFO, "Checking: %s\n", d->name);
av_assert0(d->log2_chroma_w <= 3);
av_assert0(d->log2_chroma_h <= 3);
av_assert0(d->nb_components <= 4);
diff --git a/libavutil/pixfmt.h b/libavutil/pixfmt.h
index 86c9bdefeb..effaac29d3 100644
--- a/libavutil/pixfmt.h
+++ b/libavutil/pixfmt.h
@@ -372,6 +372,18 @@ enum AVPixelFormat {
AV_PIX_FMT_RGBAF16BE, ///< IEEE-754 half precision packed RGBA 16:16:16:16, 64bpp, RGBARGBA..., big-endian
AV_PIX_FMT_RGBAF16LE, ///< IEEE-754 half precision packed RGBA 16:16:16:16, 64bpp, RGBARGBA..., little-endian
+ AV_PIX_FMT_P012LE, ///< like NV12, with 12bpp per component, data in the high bits, zeros in the low bits, little-endian
+ AV_PIX_FMT_P012BE, ///< like NV12, with 12bpp per component, data in the high bits, zeros in the low bits, big-endian
+
+ AV_PIX_FMT_Y212BE, ///< packed YUV 4:2:2 like YUYV422, 24bpp, data in the high bits, zeros in the low bits, big-endian
+ AV_PIX_FMT_Y212LE, ///< packed YUV 4:2:2 like YUYV422, 24bpp, data in the high bits, zeros in the low bits, little-endian
+
+ AV_PIX_FMT_Y410BE, ///< packed AVYU 4:4:4:4, 32bpp, (msb)2A 10V 10Y 10U(lsb), big-endian
+ AV_PIX_FMT_Y410LE, ///< packed AVYU 4:4:4:4, 32bpp, (msb)2A 10V 10Y 10U(lsb), little-endian
+
+ AV_PIX_FMT_Y412BE, ///< packed AVYU 4:4:4:4, 48bpp, data in the high bits, zeros in the low bits, big-endian
+ AV_PIX_FMT_Y412LE, ///< packed AVYU 4:4:4:4, 48bpp, data in the high bits, zeros in the low bits, little-endian
+
AV_PIX_FMT_NB ///< number of pixel formats, DO NOT USE THIS if you want to link with shared libav* because the number of formats might differ between versions
};
@@ -458,9 +470,13 @@ enum AVPixelFormat {
#define AV_PIX_FMT_NV20 AV_PIX_FMT_NE(NV20BE, NV20LE)
#define AV_PIX_FMT_AYUV64 AV_PIX_FMT_NE(AYUV64BE, AYUV64LE)
#define AV_PIX_FMT_P010 AV_PIX_FMT_NE(P010BE, P010LE)
+#define AV_PIX_FMT_P012 AV_PIX_FMT_NE(P012BE, P012LE)
#define AV_PIX_FMT_P016 AV_PIX_FMT_NE(P016BE, P016LE)
#define AV_PIX_FMT_Y210 AV_PIX_FMT_NE(Y210BE, Y210LE)
+#define AV_PIX_FMT_Y212 AV_PIX_FMT_NE(Y212BE, Y212LE)
+#define AV_PIX_FMT_Y410 AV_PIX_FMT_NE(Y410BE, Y410LE)
+#define AV_PIX_FMT_Y412 AV_PIX_FMT_NE(Y412BE, Y412LE)
#define AV_PIX_FMT_X2RGB10 AV_PIX_FMT_NE(X2RGB10BE, X2RGB10LE)
#define AV_PIX_FMT_X2BGR10 AV_PIX_FMT_NE(X2BGR10BE, X2BGR10LE)
diff --git a/tests/ref/fate/imgutils b/tests/ref/fate/imgutils
index 01c9877de5..bc12d8dad4 100644
--- a/tests/ref/fate/imgutils
+++ b/tests/ref/fate/imgutils
@@ -249,3 +249,11 @@ p416le planes: 2, linesizes: 128 256 0 0, plane_sizes: 6144 12288
vuya planes: 1, linesizes: 256 0 0 0, plane_sizes: 12288 0 0 0, plane_offsets: 0 0 0, total_size: 12288
rgbaf16be planes: 1, linesizes: 512 0 0 0, plane_sizes: 24576 0 0 0, plane_offsets: 0 0 0, total_size: 24576
rgbaf16le planes: 1, linesizes: 512 0 0 0, plane_sizes: 24576 0 0 0, plane_offsets: 0 0 0, total_size: 24576
+p012le planes: 2, linesizes: 128 128 0 0, plane_sizes: 6144 3072 0 0, plane_offsets: 6144 0 0, total_size: 9216
+p012be planes: 2, linesizes: 128 128 0 0, plane_sizes: 6144 3072 0 0, plane_offsets: 6144 0 0, total_size: 9216
+y212be planes: 1, linesizes: 256 0 0 0, plane_sizes: 12288 0 0 0, plane_offsets: 0 0 0, total_size: 12288
+y212le planes: 1, linesizes: 256 0 0 0, plane_sizes: 12288 0 0 0, plane_offsets: 0 0 0, total_size: 12288
+y410be planes: 1, linesizes: 256 0 0 0, plane_sizes: 12288 0 0 0, plane_offsets: 0 0 0, total_size: 12288
+y410le planes: 1, linesizes: 256 0 0 0, plane_sizes: 12288 0 0 0, plane_offsets: 0 0 0, total_size: 12288
+y412be planes: 1, linesizes: 512 0 0 0, plane_sizes: 24576 0 0 0, plane_offsets: 0 0 0, total_size: 24576
+y412le planes: 1, linesizes: 512 0 0 0, plane_sizes: 24576 0 0 0, plane_offsets: 0 0 0, total_size: 24576
diff --git a/tests/ref/fate/sws-pixdesc-query b/tests/ref/fate/sws-pixdesc-query
index f79d99e513..04baf6a3fa 100644
--- a/tests/ref/fate/sws-pixdesc-query
+++ b/tests/ref/fate/sws-pixdesc-query
@@ -63,6 +63,8 @@ isNBPS:
nv20le
p010be
p010le
+ p012be
+ p012le
p210be
p210le
p410be
@@ -75,6 +77,12 @@ isNBPS:
xyz12le
y210be
y210le
+ y212be
+ y212le
+ y410be
+ y410le
+ y412be
+ y412le
yuv420p10be
yuv420p10le
yuv420p12be
@@ -149,6 +157,7 @@ isBE:
grayf32be
nv20be
p010be
+ p012be
p016be
p210be
p216be
@@ -164,6 +173,9 @@ isBE:
x2rgb10be
xyz12be
y210be
+ y212be
+ y410be
+ y412be
ya16be
yuv420p10be
yuv420p12be
@@ -206,6 +218,8 @@ isYUV:
nv42
p010be
p010le
+ p012be
+ p012le
p016be
p016le
p210be
@@ -223,6 +237,12 @@ isYUV:
xyz12le
y210be
y210le
+ y212be
+ y212le
+ y410be
+ y410le
+ y412be
+ y412le
ya16be
ya16le
ya8
@@ -309,6 +329,8 @@ isPlanarYUV:
nv42
p010be
p010le
+ p012be
+ p012le
p016be
p016le
p210be
@@ -400,6 +422,8 @@ isSemiPlanarYUV:
nv42
p010be
p010le
+ p012be
+ p012le
p016be
p016le
p210be
@@ -665,6 +689,10 @@ ALPHA:
rgbaf16be
rgbaf16le
vuya
+ y410be
+ y410le
+ y412be
+ y412le
ya16be
ya16le
ya8
@@ -761,6 +789,12 @@ Packed:
xyz12le
y210be
y210le
+ y212be
+ y212le
+ y410be
+ y410le
+ y412be
+ y412le
ya16be
ya16le
ya8
@@ -799,6 +833,8 @@ Planar:
nv42
p010be
p010le
+ p012be
+ p012le
p016be
p016le
p210be
@@ -971,6 +1007,8 @@ usePal:
DataInHighBits:
p010be
p010le
+ p012be
+ p012le
p210be
p210le
p410be
@@ -979,6 +1017,10 @@ DataInHighBits:
xyz12le
y210be
y210le
+ y212be
+ y212le
+ y412be
+ y412le
SwappedChroma:
nv21
--
2.34.1
More information about the ffmpeg-devel
mailing list