avfilter/vf_yadif_cuda: CUDA accelerated yadif deinterlacer

This is a cuda implementation of yadif, which gives us a way to
do deinterlacing when using the nvdec hwaccel. In that scenario
we don't have access to the nvidia deinterlacer.

Changelog

@@ -45,6 +45,7 @@ version 4.1:
 - xstack filter
 - pcm vidc decoder and encoder
 - (a)graphmonitor filter
+- yadif_cuda filter
 
 
 version 4.0:

configure

@@ -3482,6 +3482,7 @@ zscale_filter_deps="libzimg const_nan"
 scale_vaapi_filter_deps="vaapi"
 vpp_qsv_filter_deps="libmfx"
 vpp_qsv_filter_select="qsvvpp"
+yadif_cuda_filter_deps="cuda_sdk"
 
 # examples
 avio_dir_cmd_deps="avformat avutil"

doc/filters.texi

@@ -17983,6 +17983,64 @@ filter").
 It accepts the following parameters:
 
 
+@table @option
+
+@item mode
+The interlacing mode to adopt. It accepts one of the following values:
+
+@table @option
+@item 0, send_frame
+Output one frame for each frame.
+@item 1, send_field
+Output one frame for each field.
+@item 2, send_frame_nospatial
+Like @code{send_frame}, but it skips the spatial interlacing check.
+@item 3, send_field_nospatial
+Like @code{send_field}, but it skips the spatial interlacing check.
+@end table
+
+The default value is @code{send_frame}.
+
+@item parity
+The picture field parity assumed for the input interlaced video. It accepts one
+of the following values:
+
+@table @option
+@item 0, tff
+Assume the top field is first.
+@item 1, bff
+Assume the bottom field is first.
+@item -1, auto
+Enable automatic detection of field parity.
+@end table
+
+The default value is @code{auto}.
+If the interlacing is unknown or the decoder does not export this information,
+top field first will be assumed.
+
+@item deint
+Specify which frames to deinterlace. Accept one of the following
+values:
+
+@table @option
+@item 0, all
+Deinterlace all frames.
+@item 1, interlaced
+Only deinterlace frames marked as interlaced.
+@end table
+
+The default value is @code{all}.
+@end table
+
+@section yadif_cuda
+
+Deinterlace the input video using the @ref{yadif} algorithm, but implemented
+in CUDA so that it can work as part of a GPU accelerated pipeline with nvdec
+and/or nvenc.
+
+It accepts the following parameters:
+
+
 @table @option
 
 @item mode

libavfilter/Makefile

@@ -409,6 +409,7 @@ OBJS-$(CONFIG_WEAVE_FILTER)                  += vf_weave.o
 OBJS-$(CONFIG_XBR_FILTER)                    += vf_xbr.o
 OBJS-$(CONFIG_XSTACK_FILTER)                 += vf_stack.o framesync.o
 OBJS-$(CONFIG_YADIF_FILTER)                  += vf_yadif.o yadif_common.o
+OBJS-$(CONFIG_YADIF_CUDA_FILTER)             += vf_yadif_cuda.o vf_yadif_cuda.ptx.o yadif_common.o
 OBJS-$(CONFIG_ZMQ_FILTER)                    += f_zmq.o
 OBJS-$(CONFIG_ZOOMPAN_FILTER)                += vf_zoompan.o
 OBJS-$(CONFIG_ZSCALE_FILTER)                 += vf_zscale.o

libavfilter/allfilters.c

@@ -390,6 +390,7 @@ extern AVFilter ff_vf_weave;
 extern AVFilter ff_vf_xbr;
 extern AVFilter ff_vf_xstack;
 extern AVFilter ff_vf_yadif;
+extern AVFilter ff_vf_yadif_cuda;
 extern AVFilter ff_vf_zmq;
 extern AVFilter ff_vf_zoompan;
 extern AVFilter ff_vf_zscale;

libavfilter/version.h

@@ -30,7 +30,7 @@
 #include "libavutil/version.h"
 
 #define LIBAVFILTER_VERSION_MAJOR   7
-#define LIBAVFILTER_VERSION_MINOR  42
+#define LIBAVFILTER_VERSION_MINOR  43
 #define LIBAVFILTER_VERSION_MICRO 100
 
 #define LIBAVFILTER_VERSION_INT AV_VERSION_INT(LIBAVFILTER_VERSION_MAJOR, \