lavu/pixdesc: favour formats where depth and subsampling exactly match

Since introducing the various packed formats used by VAAPI (and p012),
we've noticed that there's actually a gap in how
av_find_best_pix_fmt_of_2 works. It doesn't actually assign any value
to having the same bit depth as the source format, when comparing
against formats with a higher bit depth. This usually doesn't matter,
because av_get_padded_bits_per_pixel() will account for it.

However, as many of these formats use padding internally, we find that
av_get_padded_bits_per_pixel() actually returns the same value for the
10 bit, 12 bit, 16 bit flavours, etc. In these tied situations, we end
up just picking the first of the two provided formats, even if the
second one should be preferred because it matches the actual bit depth.

This bug already existed if you tried to compare yuv420p10 against p016
and p010, for example, but it simply hadn't come up before so we never
noticed.

But now, we actually got a situation in the VAAPI VP9 decoder where it
offers both p010 and p012 because Profile 3 could be either depth and
ends up picking p012 for 10 bit content due to the ordering of the
testing.

In addition, in the process of testing the fix, I realised we have the
same gap when it comes to chroma subsampling - we do not favour a
format that has exactly the same subsampling vs one with less
subsampling when all else is equal.

To fix this, I'm introducing a small score penalty if the bit depth or
subsampling doesn't exactly match the source format. This will break
the tie in favour of the format with the exact match, but not offset
any of the other scoring penalties we already have.

I have added a set of tests around these formats which will fail
without this fix.

5 files changed, 151 insertions, 28 deletions

diff --git a/libavutil/pixdesc.c b/libavutil/pixdesc.c
index d7c6ebfdc4..b472a94f60 100644
--- a/libavutil/pixdesc.c
+++ b/libavutil/pixdesc.c
@@ -3013,9 +3013,16 @@ static int get_pix_fmt_score(enum AVPixelFormat dst_pix_fmt,
 
     for (i = 0; i < nb_components; i++) {
         int depth_minus1 = (dst_pix_fmt == AV_PIX_FMT_PAL8) ? 7/nb_components : (dst_desc->comp[i].depth - 1);
-        if (src_desc->comp[i].depth - 1 > depth_minus1 && (consider & FF_LOSS_DEPTH)) {
+        int depth_delta = src_desc->comp[i].depth - 1 - depth_minus1;
+        if (depth_delta > 0 && (consider & FF_LOSS_DEPTH)) {
             loss |= FF_LOSS_DEPTH;
             score -= 65536 >> depth_minus1;
+        } else if (depth_delta < 0 && (consider & FF_LOSS_EXCESS_DEPTH)) {
+            // Favour formats where bit depth exactly matches. If all other
+            // scoring is equal, we'd rather use the bit depth that most closely
+            // matches the source.
+            loss |= FF_LOSS_EXCESS_DEPTH;
+            score += depth_delta;
         }
     }
 
@@ -3035,6 +3042,28 @@ static int get_pix_fmt_score(enum AVPixelFormat dst_pix_fmt,
         }
     }
 
+    if (consider & FF_LOSS_EXCESS_RESOLUTION) {
+        // Favour formats where chroma subsampling exactly matches. If all other
+        // scoring is equal, we'd rather use the subsampling that most closely
+        // matches the source.
+        if (dst_desc->log2_chroma_w < src_desc->log2_chroma_w) {
+            loss |= FF_LOSS_EXCESS_RESOLUTION;
+            score -= 1 << (src_desc->log2_chroma_w - dst_desc->log2_chroma_w);
+        }
+
+        if (dst_desc->log2_chroma_h < src_desc->log2_chroma_h) {
+            loss |= FF_LOSS_EXCESS_RESOLUTION;
+            score -= 1 << (src_desc->log2_chroma_h - dst_desc->log2_chroma_h);
+        }
+
+        // don't favour 411 over 420, because 420 has much better support on the
+        // decoder side.
+        if (dst_desc->log2_chroma_w == 1 && src_desc->log2_chroma_w == 2 &&
+            dst_desc->log2_chroma_h == 1 && src_desc->log2_chroma_h == 2) {
+                score += 4;
+            }
+    }
+
     if(consider & FF_LOSS_COLORSPACE)
     switch(dst_color) {
     case FF_COLOR_RGB:
diff --git a/libavutil/pixdesc.h b/libavutil/pixdesc.h
index f8a195ffcd..48d9300bfe 100644
--- a/libavutil/pixdesc.h
+++ b/libavutil/pixdesc.h
@@ -357,12 +357,15 @@ void av_write_image_line(const uint16_t *src, uint8_t *data[4],
  */
 enum AVPixelFormat av_pix_fmt_swap_endianness(enum AVPixelFormat pix_fmt);
 
-#define FF_LOSS_RESOLUTION  0x0001 /**< loss due to resolution change */
-#define FF_LOSS_DEPTH       0x0002 /**< loss due to color depth change */
-#define FF_LOSS_COLORSPACE  0x0004 /**< loss due to color space conversion */
-#define FF_LOSS_ALPHA       0x0008 /**< loss of alpha bits */
-#define FF_LOSS_COLORQUANT  0x0010 /**< loss due to color quantization */
-#define FF_LOSS_CHROMA      0x0020 /**< loss of chroma (e.g. RGB to gray conversion) */
+#define FF_LOSS_RESOLUTION        0x0001 /**< loss due to resolution change */
+#define FF_LOSS_DEPTH             0x0002 /**< loss due to color depth change */
+#define FF_LOSS_COLORSPACE        0x0004 /**< loss due to color space conversion */
+#define FF_LOSS_ALPHA             0x0008 /**< loss of alpha bits */
+#define FF_LOSS_COLORQUANT        0x0010 /**< loss due to color quantization */
+#define FF_LOSS_CHROMA            0x0020 /**< loss of chroma (e.g. RGB to gray conversion) */
+#define FF_LOSS_EXCESS_RESOLUTION 0x0040 /**< loss due to unneeded extra resolution */
+#define FF_LOSS_EXCESS_DEPTH      0x0080 /**< loss due to unneeded extra color depth */
+
 
 /**
  * Compute what kind of losses will occur when converting from one specific
diff --git a/libavutil/tests/pixfmt_best.c b/libavutil/tests/pixfmt_best.c
index 0542af494f..d71b3cc2e8 100644
--- a/libavutil/tests/pixfmt_best.c
+++ b/libavutil/tests/pixfmt_best.c
@@ -39,32 +39,74 @@ static const enum AVPixelFormat pixfmt_list[] = {
     AV_PIX_FMT_VAAPI,
 };
 
-static enum AVPixelFormat find_best(enum AVPixelFormat pixfmt)
+static const enum AVPixelFormat semiplanar_list[] = {
+    AV_PIX_FMT_P016,
+    AV_PIX_FMT_P012,
+    AV_PIX_FMT_P010,
+    AV_PIX_FMT_NV12,
+};
+
+static const enum AVPixelFormat packed_list[] = {
+    AV_PIX_FMT_XV36,
+    AV_PIX_FMT_XV30,
+    AV_PIX_FMT_VUYX,
+    AV_PIX_FMT_Y212,
+    AV_PIX_FMT_Y210,
+    AV_PIX_FMT_YUYV422,
+};
+
+static const enum AVPixelFormat subsampled_list[] = {
+    AV_PIX_FMT_YUV411P,
+    AV_PIX_FMT_YUV420P,
+    AV_PIX_FMT_YUV422P,
+    AV_PIX_FMT_YUV444P,
+};
+
+static const enum AVPixelFormat depthchroma_list[] = {
+    AV_PIX_FMT_YUV420P14,
+    AV_PIX_FMT_YUV422P14,
+    AV_PIX_FMT_YUV444P16,
+};
+
+typedef enum AVPixelFormat (*find_best_t)(enum AVPixelFormat pixfmt);
+
+#define find_best_wrapper(name, list) \
+static enum AVPixelFormat find_best_ ## name (enum AVPixelFormat pixfmt)    \
+{                                                                           \
+    enum AVPixelFormat best = AV_PIX_FMT_NONE;                              \
+    int i;                                                                  \
+    for (i = 0; i < FF_ARRAY_ELEMS(list); i++)                              \
+        best = av_find_best_pix_fmt_of_2(best, list[i],                     \
+                                         pixfmt, 0, NULL);                  \
+    return best;                                                            \
+}
+
+find_best_wrapper(base, pixfmt_list)
+find_best_wrapper(seminplanar, semiplanar_list)
+find_best_wrapper(packed, packed_list)
+find_best_wrapper(subsampled, subsampled_list)
+find_best_wrapper(depthchroma, depthchroma_list)
+
+static void test(enum AVPixelFormat input, enum AVPixelFormat expected,
+                 int *pass, int *fail, find_best_t find_best_fn)
 {
-    enum AVPixelFormat best = AV_PIX_FMT_NONE;
-    int i;
-    for (i = 0; i < FF_ARRAY_ELEMS(pixfmt_list); i++)
-        best = av_find_best_pix_fmt_of_2(best, pixfmt_list[i],
-                                         pixfmt, 0, NULL);
-    return best;
+        enum AVPixelFormat output = find_best_fn(input);
+        if (output != expected) {
+            printf("Matching %s: got %s, expected %s\n",
+                   av_get_pix_fmt_name(input),
+                   av_get_pix_fmt_name(output),
+                   av_get_pix_fmt_name(expected));
+            ++(*fail);
+        } else
+            ++(*pass);
 }
 
 int main(void)
 {
-    enum AVPixelFormat output;
     int i, pass = 0, fail = 0;
 
-#define TEST(input, expected) do {                              \
-        output = find_best(input);                              \
-        if (output != expected) {                               \
-            printf("Matching %s: got %s, expected %s\n",        \
-                   av_get_pix_fmt_name(input),                  \
-                   av_get_pix_fmt_name(output),                 \
-                   av_get_pix_fmt_name(expected));              \
-            ++fail;                                             \
-        } else                                                  \
-            ++pass;                                             \
-    } while (0)
+#define TEST(input, expected) \
+    test(input, expected, &pass, &fail, find_best_base)
 
     // Same formats.
     for (i = 0; i < FF_ARRAY_ELEMS(pixfmt_list); i++)
@@ -137,6 +179,55 @@ int main(void)
     // Opaque formats are least unlike each other.
     TEST(AV_PIX_FMT_DXVA2_VLD, AV_PIX_FMT_VDPAU);
 
+#define TEST_SEMIPLANAR(input, expected) \
+    test(input, expected, &pass, &fail, find_best_seminplanar)
+
+    // Same formats.
+    for (i = 0; i < FF_ARRAY_ELEMS(semiplanar_list); i++)
+        TEST_SEMIPLANAR(semiplanar_list[i], semiplanar_list[i]);
+
+    // Formats containing the same data in different layouts.
+    TEST_SEMIPLANAR(AV_PIX_FMT_YUV420P, AV_PIX_FMT_NV12);
+    TEST_SEMIPLANAR(AV_PIX_FMT_YUV420P10, AV_PIX_FMT_P010);
+    TEST_SEMIPLANAR(AV_PIX_FMT_YUV420P12, AV_PIX_FMT_P012);
+    TEST_SEMIPLANAR(AV_PIX_FMT_YUV420P16, AV_PIX_FMT_P016);
+    TEST_SEMIPLANAR(AV_PIX_FMT_YUV420P9, AV_PIX_FMT_P010);
+
+#define TEST_PACKED(input, expected) \
+    test(input, expected, &pass, &fail, find_best_packed)
+
+    // Same formats.
+    for (i = 0; i < FF_ARRAY_ELEMS(packed_list); i++)
+        TEST_PACKED(packed_list[i], packed_list[i]);
+
+    // Formats containing the same data in different layouts.
+    TEST_PACKED(AV_PIX_FMT_YUV444P, AV_PIX_FMT_VUYX);
+    TEST_PACKED(AV_PIX_FMT_YUV444P10, AV_PIX_FMT_XV30);
+    TEST_PACKED(AV_PIX_FMT_YUV444P12, AV_PIX_FMT_XV36);
+    TEST_PACKED(AV_PIX_FMT_YUV422P, AV_PIX_FMT_YUYV422);
+    TEST_PACKED(AV_PIX_FMT_YUV422P10, AV_PIX_FMT_Y210);
+    TEST_PACKED(AV_PIX_FMT_YUV422P12, AV_PIX_FMT_Y212);
+
+#define TEST_SUBSAMPLED(input, expected) \
+    test(input, expected, &pass, &fail, find_best_subsampled)
+
+    // Same formats.
+    for (i = 0; i < FF_ARRAY_ELEMS(subsampled_list); i++)
+        TEST_SUBSAMPLED(subsampled_list[i], subsampled_list[i]);
+
+    TEST_SUBSAMPLED(AV_PIX_FMT_YUV410P, AV_PIX_FMT_YUV420P);
+
+#define TEST_DEPTH_CHROMA(input, expected) \
+    test(input, expected, &pass, &fail, find_best_depthchroma)
+
+    // Same formats.
+    for (i = 0; i < FF_ARRAY_ELEMS(depthchroma_list); i++)
+        TEST_DEPTH_CHROMA(depthchroma_list[i], depthchroma_list[i]);
+
+    TEST_DEPTH_CHROMA(AV_PIX_FMT_YUV420P16, AV_PIX_FMT_YUV444P16);
+    TEST_DEPTH_CHROMA(AV_PIX_FMT_YUV422P16, AV_PIX_FMT_YUV444P16);
+
+
     printf("%d tests passed, %d tests failed.\n", pass, fail);
     return !!fail;
 }
diff --git a/libavutil/version.h b/libavutil/version.h
index 9b8462c705..0585fa7b80 100644
--- a/libavutil/version.h
+++ b/libavutil/version.h
@@ -80,7 +80,7 @@
 
 #define LIBAVUTIL_VERSION_MAJOR  57
 #define LIBAVUTIL_VERSION_MINOR  36
-#define LIBAVUTIL_VERSION_MICRO 101
+#define LIBAVUTIL_VERSION_MICRO 102
 
 #define LIBAVUTIL_VERSION_INT   AV_VERSION_INT(LIBAVUTIL_VERSION_MAJOR, \
                                                LIBAVUTIL_VERSION_MINOR, \
diff --git a/tests/ref/fate/pixfmt_best b/tests/ref/fate/pixfmt_best
index 783c5fe640..1bdc0e83f0 100644
--- a/tests/ref/fate/pixfmt_best
+++ b/tests/ref/fate/pixfmt_best
@@ -1 +1 @@
-75 tests passed, 0 tests failed.
+106 tests passed, 0 tests failed.