[FFmpeg-devel] [PATCH] libavcodec: add tune_content option also for VP8.

[Dariusz Marcinkiewicz]

Please ignore this version of the patch. I'll send out v2 soon. Apologies
for the noise.

On Thu, Jan 25, 2024 at 6:13 PM Dariusz Marcinkiewicz <darekm at google.com>
wrote:

> This exposes VP8E_SET_SCREEN_CONTENT_MODE option from libvpx.
>
> Change authored by Erik Språng <sprang at webrtc.org>
>
> Signed-off-by: Dariusz Marcinkiewicz <darekm at google.com>
> ---
>  doc/encoders.texi      |  7 +++++--
>  libavcodec/libvpxenc.c | 35 ++++++++++++++++++++++++++++++++++-
>  2 files changed, 39 insertions(+), 3 deletions(-)
>
> diff --git a/doc/encoders.texi b/doc/encoders.texi
> index c9fe6d6143..2a9b38f62a 100644
> --- a/doc/encoders.texi
> +++ b/doc/encoders.texi
> @@ -2186,6 +2186,11 @@ Enable error resiliency features.
>  Increase sharpness at the expense of lower PSNR.
>  The valid range is [0, 7].
>
> + at item tune-content
> +Set content type.
> +For VP8: default (0), screen (1), screen with aggressive rate control (2).
> +For VP9: default (0), screen (1), film (2).
> +
>  @item ts-parameters
>  Sets the temporal scalability configuration using a :-separated list of
>  key=value pairs. For example, to specify temporal scalability parameters
> @@ -2268,8 +2273,6 @@ colorspaces:
>  @end table
>  @item row-mt @var{boolean}
>  Enable row based multi-threading.
> - at item tune-content
> -Set content type: default (0), screen (1), film (2).
>  @item corpus-complexity
>  Corpus VBR mode is a variant of standard VBR where the complexity
> distribution
>  midpoint is passed in rather than calculated for a specific clip or chunk.
> diff --git a/libavcodec/libvpxenc.c b/libavcodec/libvpxenc.c
> index 80988a2608..c28cca40a2 100644
> --- a/libavcodec/libvpxenc.c
> +++ b/libavcodec/libvpxenc.c
> @@ -164,6 +164,7 @@ static const char *const ctlidstr[] = {
>      [VP8E_SET_MAX_INTRA_BITRATE_PCT] = "VP8E_SET_MAX_INTRA_BITRATE_PCT",
>      [VP8E_SET_SHARPNESS]               = "VP8E_SET_SHARPNESS",
>      [VP8E_SET_TEMPORAL_LAYER_ID]       = "VP8E_SET_TEMPORAL_LAYER_ID",
> +    [VP8E_SET_SCREEN_CONTENT_MODE]     = "VP8E_SET_SCREEN_CONTENT_MODE",
>  #if CONFIG_LIBVPX_VP9_ENCODER
>      [VP9E_SET_LOSSLESS]                = "VP9E_SET_LOSSLESS",
>      [VP9E_SET_TILE_COLUMNS]            = "VP9E_SET_TILE_COLUMNS",
> @@ -1249,8 +1250,19 @@ static av_cold int vpx_init(AVCodecContext *avctx,
>              codecctl_int(avctx, VP9E_SET_ROW_MT, ctx->row_mt);
>  #endif
>  #ifdef VPX_CTRL_VP9E_SET_TUNE_CONTENT
> -        if (ctx->tune_content >= 0)
> +        if (ctx->tune_content >= 0 && avctx->codec_id == AV_CODEC_ID_VP9)
> {
>              codecctl_int(avctx, VP9E_SET_TUNE_CONTENT, ctx->tune_content);
> +        }
> +#endif
> +#ifdef VPX_CTRL_VP8E_SET_SCREEN_CONTENT_MODE
> +        if (ctx->tune_content >= 0 && avctx->codec_id == AV_CODEC_ID_VP8)
> {
> +          if (ctx->tune_content == 2 && ctx->is_alpha) {
> +            av_log(avctx, AV_LOG_ERROR,
> +                   "Transparency encoding with screen mode with
> aggressive rate control not supported\n");
> +            return AVERROR(EINVAL);
> +          }
> +          codecctl_int(avctx, VP8E_SET_SCREEN_CONTENT_MODE,
> ctx->tune_content);
> +        }
>  #endif
>  #ifdef VPX_CTRL_VP9E_SET_TPL
>          if (ctx->tpl_model >= 0)
> @@ -1857,6 +1869,21 @@ FF_ENABLE_DEPRECATION_WARNINGS
>      }
>
>      coded_size = queue_frames(avctx, &ctx->encoder,
> &ctx->coded_frame_list, pkt);
> +    if (avctx->codec_id == AV_CODEC_ID_VP8 && coded_size == 0 &&
> ctx->tune_content == 2) {
> +        // VP8 tuned for screen content with aggresive rate control -
> returned
> +        // OK status code but produced no output, this indicates frame was
> +        // rolled back due to bitrate overshoot - try to encode it again.
> +        av_log(avctx, AV_LOG_VERBOSE,
> +               "Attempting to reencode dropped VP8 screencast frame.");
> +        res = vpx_codec_encode(&ctx->encoder, rawimg, timestamp,
> +                               avctx->ticks_per_frame, flags,
> ctx->deadline);
> +        if (res != VPX_CODEC_OK) {
> +            log_encoder_error(avctx, "Error encoding frame");
> +            return AVERROR_INVALIDDATA;
> +        }
> +        coded_size = queue_frames(avctx, &ctx->encoder,
> &ctx->coded_frame_list, pkt);
> +    }
> +
>      if (ctx->is_alpha) {
>          queue_frames(avctx, &ctx->encoder_alpha,
> &ctx->alpha_coded_frame_list, NULL);
>
> @@ -1946,6 +1973,12 @@ static const AVOption vp8_options[] = {
>      { "auto-alt-ref",    "Enable use of alternate reference "
>                           "frames (2-pass only)",
> OFFSET(auto_alt_ref),    AV_OPT_TYPE_INT, {.i64 = -1}, -1,  2, VE},
>      { "cpu-used",        "Quality/Speed ratio modifier",
> OFFSET(cpu_used),        AV_OPT_TYPE_INT, {.i64 = 1}, -16, 16, VE},
> +    { "tune-content",     "Tune content type",
> OFFSET(tune_content),    AV_OPT_TYPE_INT, {.i64 = -1}, -1,  2, VE,
> "tune_content"},
> +#ifdef VPX_CTRL_VP8E_SET_SCREEN_CONTENT_MODE
> +    { "default",          "Regular video content",
> 0,                       AV_OPT_TYPE_CONST, {.i64 = 0}, 0,  0, VE,
> "tune_content"},
> +    { "screen",           "Screen content mode on",
>  0,                       AV_OPT_TYPE_CONST, {.i64 = 1}, 0,  0, VE,
> "tune_content"},
> +    { "screen-rate-control", "Screen content mode with aggressive rate
> control", 0,              AV_OPT_TYPE_CONST, {.i64 = 2}, 0,  0, VE,
> "tune_content"},
> +#endif
>      LEGACY_OPTIONS
>      { NULL }
>  };
> --
> 2.43.0.429.g432eaa2c6b-goog
>
>