@@ -2780,6 +2780,7 @@ repeatfields_filter_deps="gpl"

 resample_filter_deps="avresample"

 sab_filter_deps="gpl swscale"

 scale_filter_deps="swscale"

+scale2ref_filter_deps="swscale"

 select_filter_select="pixelutils"

 smartblur_filter_deps="gpl swscale"

 showcqt_filter_deps="avcodec"

@@ -5831,6 +5832,7 @@ enabled removelogo_filter   && prepend avfilter_deps "avformat avcodec swscale"

 enabled resample_filter && prepend avfilter_deps "avresample"

 enabled sab_filter          && prepend avfilter_deps "swscale"

 enabled scale_filter    && prepend avfilter_deps "swscale"

+enabled scale2ref_filter    && prepend avfilter_deps "swscale"

 enabled showspectrum_filter && prepend avfilter_deps "avcodec"

 enabled smartblur_filter    && prepend avfilter_deps "swscale"

 enabled subtitles_filter    && prepend avfilter_deps "avformat avcodec"

@@ -9122,6 +9122,23 @@ If the specified expression is not valid, it is kept at its current

 value.

 @end table

+@section scale2ref

+

+Scale (resize) the input video, based on a reference video.

+

+See the scale filter for available options, scale2ref supports the same but

+uses the reference video instead of the main input as basis.

+

+@subsection Examples

+

+@itemize

+@item

+Scale a subtitle stream to match the main video in size before overlaying

+@example

+'scale2ref[b][a];[a][b]overlay'

+@end example

+@end itemize

+

 @section separatefields

 The @code{separatefields} takes a frame-based video input and splits

@@ -197,6 +197,7 @@ OBJS-$(CONFIG_ROTATE_FILTER)                 += vf_rotate.o

 OBJS-$(CONFIG_SEPARATEFIELDS_FILTER)         += vf_separatefields.o

 OBJS-$(CONFIG_SAB_FILTER)                    += vf_sab.o

 OBJS-$(CONFIG_SCALE_FILTER)                  += vf_scale.o

+OBJS-$(CONFIG_SCALE2REF_FILTER)              += vf_scale.o

 OBJS-$(CONFIG_SELECT_FILTER)                 += f_select.o

 OBJS-$(CONFIG_SENDCMD_FILTER)                += f_sendcmd.o

 OBJS-$(CONFIG_SETDAR_FILTER)                 += vf_aspect.o

@@ -211,6 +211,7 @@ void avfilter_register_all(void)

     REGISTER_FILTER(ROTATE,         rotate,         vf);

     REGISTER_FILTER(SAB,            sab,            vf);

     REGISTER_FILTER(SCALE,          scale,          vf);

+    REGISTER_FILTER(SCALE2REF,      scale2ref,      vf);

     REGISTER_FILTER(SELECT,         select,         vf);

     REGISTER_FILTER(SENDCMD,        sendcmd,        vf);

     REGISTER_FILTER(SEPARATEFIELDS, separatefields, vf);

@@ -30,7 +30,7 @@

 #include "libavutil/version.h"

 #define LIBAVFILTER_VERSION_MAJOR  5

-#define LIBAVFILTER_VERSION_MINOR  33

+#define LIBAVFILTER_VERSION_MINOR  34

 #define LIBAVFILTER_VERSION_MICRO 100

 #define LIBAVFILTER_VERSION_INT AV_VERSION_INT(LIBAVFILTER_VERSION_MAJOR, \

@@ -111,6 +111,8 @@ typedef struct ScaleContext {

     int force_original_aspect_ratio;

 } ScaleContext;

+AVFilter ff_vf_scale2ref;

+

 static av_cold int init_dict(AVFilterContext *ctx, AVDictionary **opts)

 {

     ScaleContext *scale = ctx->priv;

@@ -234,7 +236,10 @@ static const int *parse_yuv_type(const char *s, enum AVColorSpace colorspace)

 static int config_props(AVFilterLink *outlink)

 {

     AVFilterContext *ctx = outlink->src;

-    AVFilterLink *inlink = outlink->src->inputs[0];

+    AVFilterLink *inlink0 = outlink->src->inputs[0];

+    AVFilterLink *inlink  = ctx->filter == &ff_vf_scale2ref ?

+                            outlink->src->inputs[1] :

+                            outlink->src->inputs[0];

     enum AVPixelFormat outfmt = outlink->format;

     ScaleContext *scale = ctx->priv;

     const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format);

@@ -343,8 +348,9 @@ static int config_props(AVFilterLink *outlink)

     if (scale->isws[1])

         sws_freeContext(scale->isws[1]);

     scale->isws[0] = scale->isws[1] = scale->sws = NULL;

-    if (inlink->w == outlink->w && inlink->h == outlink->h &&

-        inlink->format == outlink->format)

+    if (inlink0->w == outlink->w &&

+        inlink0->h == outlink->h &&

+        inlink0->format == outlink->format)

         ;

     else {

         struct SwsContext **swscs[3] = {&scale->sws, &scale->isws[0], &scale->isws[1]};

@@ -356,9 +362,9 @@ static int config_props(AVFilterLink *outlink)

             if (!*s)

                 return AVERROR(ENOMEM);

-            av_opt_set_int(*s, "srcw", inlink ->w, 0);

-            av_opt_set_int(*s, "srch", inlink ->h >> !!i, 0);

-            av_opt_set_int(*s, "src_format", inlink->format, 0);

+            av_opt_set_int(*s, "srcw", inlink0 ->w, 0);

+            av_opt_set_int(*s, "srch", inlink0 ->h >> !!i, 0);

+            av_opt_set_int(*s, "src_format", inlink0->format, 0);

             av_opt_set_int(*s, "dstw", outlink->w, 0);

             av_opt_set_int(*s, "dsth", outlink->h >> !!i, 0);

             av_opt_set_int(*s, "dst_format", outfmt, 0);

@@ -374,7 +380,7 @@ static int config_props(AVFilterLink *outlink)

             /* Override YUV420P settings to have the correct (MPEG-2) chroma positions

              * MPEG-2 chroma positions are used by convention

              * XXX: support other 4:2:0 pixel formats */

-            if (inlink->format == AV_PIX_FMT_YUV420P) {

+            if (inlink0->format == AV_PIX_FMT_YUV420P) {

                 scale->in_v_chr_pos = (i == 0) ? 128 : (i == 1) ? 64 : 192;

             }

@@ -415,6 +421,17 @@ fail:

     return ret;

 }

+static int config_props_ref(AVFilterLink *outlink)

+{

+    AVFilterLink *inlink = outlink->src->inputs[1];

+

+    outlink->w = inlink->w;

+    outlink->h = inlink->h;

+    outlink->sample_aspect_ratio = inlink->sample_aspect_ratio;

+

+    return 0;

+}

+

 static int scale_slice(AVFilterLink *link, AVFrame *out_buf, AVFrame *cur_pic, struct SwsContext *sws, int y, int h, int mul, int field)

 {

     ScaleContext *scale = link->dst->priv;

@@ -542,6 +559,13 @@ static int filter_frame(AVFilterLink *link, AVFrame *in)

     return ff_filter_frame(outlink, out);

 }

+static int filter_frame_ref(AVFilterLink *link, AVFrame *in)

+{

+    AVFilterLink *outlink = link->dst->outputs[1];

+

+    return ff_filter_frame(outlink, in);

+}

+

 static int process_command(AVFilterContext *ctx, const char *cmd, const char *args,

                            char *res, int res_len, int flags)

 {

@@ -643,3 +667,53 @@ AVFilter ff_vf_scale = {

     .outputs         = avfilter_vf_scale_outputs,

     .process_command = process_command,

 };

+

+static const AVClass scale2ref_class = {

+    .class_name       = "scale2ref",

+    .item_name        = av_default_item_name,

+    .option           = scale_options,

+    .version          = LIBAVUTIL_VERSION_INT,

+    .category         = AV_CLASS_CATEGORY_FILTER,

+    .child_class_next = child_class_next,

+};

+

+static const AVFilterPad avfilter_vf_scale2ref_inputs[] = {

+    {

+        .name         = "default",

+        .type         = AVMEDIA_TYPE_VIDEO,

+        .filter_frame = filter_frame,

+    },

+    {

+        .name         = "ref",

+        .type         = AVMEDIA_TYPE_VIDEO,

+        .filter_frame = filter_frame_ref,

+    },

+    { NULL }

+};

+

+static const AVFilterPad avfilter_vf_scale2ref_outputs[] = {

+    {

+        .name         = "default",

+        .type         = AVMEDIA_TYPE_VIDEO,

+        .config_props = config_props,

+    },

+    {

+        .name         = "ref",

+        .type         = AVMEDIA_TYPE_VIDEO,

+        .config_props = config_props_ref,

+    },

+    { NULL }

+};

+

+AVFilter ff_vf_scale2ref = {

+    .name            = "scale2ref",

+    .description     = NULL_IF_CONFIG_SMALL("Scale the input video size and/or convert the image format to the given reference."),

+    .init_dict       = init_dict,

+    .uninit          = uninit,

+    .query_formats   = query_formats,

+    .priv_size       = sizeof(ScaleContext),

+    .priv_class      = &scale2ref_class,

+    .inputs          = avfilter_vf_scale2ref_inputs,

+    .outputs         = avfilter_vf_scale2ref_outputs,

+    .process_command = process_command,

+};