diff mbox series

[FFmpeg-devel,3/3] avcodec/mediacodecenc: workaround the alignment requirement for H.265

Message ID tencent_6819C159B46C6A8A01A168167EA6AD02390A@qq.com
State Accepted
Commit 7d46ab9e1206b09ebe1a94ecac49cc99d9b3522e
Headers show
Series [FFmpeg-devel,1/3] avcodec/h265_metadata: Add options to set width/height after crop | expand

Checks

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

Commit Message

Zhao Zhili May 23, 2024, 7:08 a.m. UTC 
From: Zhao Zhili <zhilizhao@tencent.com>

Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
---
 libavcodec/mediacodecenc.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

Comments

Zhao Zhili May 23, 2024, 3:23 p.m. UTC | #1 
> On May 23, 2024, at 15:08, Zhao Zhili <quinkblack@foxmail.com> wrote:
> 
> From: Zhao Zhili <zhilizhao@tencent.com>
> 
> Signed-off-by: Zhao Zhili <zhilizhao@tencent.com>
> ---
> libavcodec/mediacodecenc.c | 11 ++++++++---
> 1 file changed, 8 insertions(+), 3 deletions(-)
> 
> diff --git a/libavcodec/mediacodecenc.c b/libavcodec/mediacodecenc.c
> index bfff149039..a42270551b 100644
> --- a/libavcodec/mediacodecenc.c
> +++ b/libavcodec/mediacodecenc.c
> @@ -154,8 +154,12 @@ static int mediacodec_init_bsf(AVCodecContext *avctx)
>             ret = snprintf(str, sizeof(str), "h264_metadata=crop_right=%d:crop_bottom=%d",
>                            crop_right, crop_bottom);
>         else if (avctx->codec_id == AV_CODEC_ID_HEVC)
> -            ret = snprintf(str, sizeof(str), "hevc_metadata=crop_right=%d:crop_bottom=%d",
> -                           crop_right, crop_bottom);
> +            /* Encoder can use CTU size larger than 16x16, so the real crop
> +             * margin can be larger than crop_right/crop_bottom. Let bsf figure
> +             * out the real crop margin.
> +             */
> +            ret = snprintf(str, sizeof(str), "hevc_metadata=width=%d:height=%d",
> +                           avctx->width, avctx->height);
>         if (ret >= sizeof(str))
>             return AVERROR_BUFFER_TOO_SMALL;
>     }
> @@ -235,7 +239,8 @@ static av_cold int mediacodec_init(AVCodecContext *avctx)
>     // Workaround the alignment requirement of mediacodec. We can't do it
>     // silently for AV_PIX_FMT_MEDIACODEC.
>     if (avctx->pix_fmt != AV_PIX_FMT_MEDIACODEC &&
> -        avctx->codec_id == AV_CODEC_ID_H264) {
> +        (avctx->codec_id == AV_CODEC_ID_H264 ||
> +         avctx->codec_id == AV_CODEC_ID_HEVC)) {
>         s->width = FFALIGN(avctx->width, 16);
>         s->height = FFALIGN(avctx->height, 16);
>     } else {
> -- 
> 2.42.0
> 

For anyone who is interested on why the workaround is important, here is an example.

This mediacodec xml comes from a pretty new mobile made by Vivo, with CPU from MTK.
Both H.264 and H.265 encoder require alignment of 16x16. MediaCodec will fail during
configure with resolution like 1080x1920. When use surface as input, it will output a video
stream with resolution 1072x1920. It’s weird, but it’s not rare.

  <MediaCodec name="c2.mtk.avc.encoder" type="video/avc" >
            <Alias name="OMX.MTK.VIDEO.ENCODER.AVC" />
            <Limit name="size" min="160x128" max="3840x2176" />
            <Limit name="alignment" value="16x16" />
            <Limit name="block-size" value="16x16" />
            <Limit name="concurrent-instances" max="10" />
            <Limit name="performance-point-3840x2160" value="30" />
            <Limit name="performance-point-1280x719" value="140" />
            <Limit name="performance-point-1280x720" value="120" />
        </MediaCodec>

  <MediaCodec name="c2.mtk.hevc.encoder" type="video/hevc" >
            <Alias name="OMX.MTK.VIDEO.ENCODER.HEVC" />
            <Limit name="size" min="160x128" max="7680x4320" />
            <Limit name="alignment" value="16x16" />
            <Limit name="block-size" value="16x16" />
            <Limit name="quality" range="0-100" default="50" />
            <Limit name="concurrent-instances" max="10" />
            <Feature name="bitrate-modes" value="VBR,CBR,CQ" />
            <Limit name="performance-point-3840x2160" value="30" />
            <Limit name="performance-point-1280x719" value="140" />
            <Limit name="performance-point-1280x720" value="120" />
        </MediaCodec>


diff mbox series

Patch

diff --git a/libavcodec/mediacodecenc.c b/libavcodec/mediacodecenc.c
index bfff149039..a42270551b 100644
--- a/libavcodec/mediacodecenc.c
+++ b/libavcodec/mediacodecenc.c
@@ -154,8 +154,12 @@  static int mediacodec_init_bsf(AVCodecContext *avctx)
             ret = snprintf(str, sizeof(str), "h264_metadata=crop_right=%d:crop_bottom=%d",
                            crop_right, crop_bottom);
         else if (avctx->codec_id == AV_CODEC_ID_HEVC)
-            ret = snprintf(str, sizeof(str), "hevc_metadata=crop_right=%d:crop_bottom=%d",
-                           crop_right, crop_bottom);
+            /* Encoder can use CTU size larger than 16x16, so the real crop
+             * margin can be larger than crop_right/crop_bottom. Let bsf figure
+             * out the real crop margin.
+             */
+            ret = snprintf(str, sizeof(str), "hevc_metadata=width=%d:height=%d",
+                           avctx->width, avctx->height);
         if (ret >= sizeof(str))
             return AVERROR_BUFFER_TOO_SMALL;
     }
@@ -235,7 +239,8 @@  static av_cold int mediacodec_init(AVCodecContext *avctx)
     // Workaround the alignment requirement of mediacodec. We can't do it
     // silently for AV_PIX_FMT_MEDIACODEC.
     if (avctx->pix_fmt != AV_PIX_FMT_MEDIACODEC &&
-        avctx->codec_id == AV_CODEC_ID_H264) {
+        (avctx->codec_id == AV_CODEC_ID_H264 ||
+         avctx->codec_id == AV_CODEC_ID_HEVC)) {
         s->width = FFALIGN(avctx->width, 16);
         s->height = FFALIGN(avctx->height, 16);
     } else {