avcodec/pngdec: Optimize has_trns code

add inner loop specialisations for 2 bpp and 4 bpp
These are all cases for which i found testsamples.

30M cycles -> 5M cycles

Testcase: fate-rgbapng-4816
Testcase: 16097/clusterfuzz-testcase-minimized-ffmpeg_AV_CODEC_ID_APNG_fuzzer-5664690889293824

Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpegSigned-off-by: Michael Niedermayer <michael@niedermayer.cc>

libavcodec/pngdec.c

@@ -24,6 +24,7 @@
 #include "libavutil/avassert.h"
 #include "libavutil/bprint.h"
 #include "libavutil/imgutils.h"
+#include "libavutil/intreadwrite.h"
 #include "libavutil/stereo3d.h"
 #include "libavutil/mastering_display_metadata.h"
 
@@ -1367,6 +1368,25 @@ exit_loop:
         for (y = 0; y < s->height; ++y) {
             uint8_t *row = &s->image_buf[s->image_linesize * y];
 
+            if (s->bpp == 2 && byte_depth == 1) {
+                uint8_t *pixel = &row[2 * s->width - 1];
+                uint8_t *rowp  = &row[1 * s->width - 1];
+                int tcolor = s->transparent_color_be[0];
+                for (x = s->width; x > 0; --x) {
+                    *pixel-- = *rowp == tcolor ? 0 : 0xff;
+                    *pixel-- = *rowp--;
+                }
+            } else if (s->bpp == 4 && byte_depth == 1) {
+                uint8_t *pixel = &row[4 * s->width - 1];
+                uint8_t *rowp  = &row[3 * s->width - 1];
+                int tcolor = AV_RL24(s->transparent_color_be);
+                for (x = s->width; x > 0; --x) {
+                    *pixel-- = AV_RL24(rowp-2) == tcolor ? 0 : 0xff;
+                    *pixel-- = *rowp--;
+                    *pixel-- = *rowp--;
+                    *pixel-- = *rowp--;
+                }
+            } else {
                 /* since we're updating in-place, we have to go from right to left */
                 for (x = s->width; x > 0; --x) {
                     uint8_t *pixel = &row[s->bpp * (x - 1)];
@@ -1380,6 +1400,7 @@ exit_loop:
                 }
             }
         }
+    }
 
     /* handle P-frames only if a predecessor frame is available */
     if (s->last_picture.f->data[0]) {