November 2021 - ffmpeg-cvslog

avformat/dashenc: enabling streaming and hls_playlist for lhls
by Zhao Zhili 05 Nov '21

05 Nov '21

ffmpeg | branch: master | Zhao Zhili <quinkblack(a)foxmail.com> | Thu Oct 21 16:15:31 2021 +0800| [a0f9650046842249233b54b1f9b4aaf03dacf0a7] | committer: James Almer avformat/dashenc: enabling streaming and hls_playlist for lhls Try to make the feature easier to use, especially since the user have enabled -strict experimental manually. The user shouldn't be surprised that hls_playlist is enabled for lhls automatically, so change the log level from warning to info for that. > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=a0f96500468422492… --- doc/muxers.texi | 2 +- libavformat/dashenc.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/doc/muxers.texi b/doc/muxers.texi index 7338e8d5d3..8febbd58bf 100644 --- a/doc/muxers.texi +++ b/doc/muxers.texi @@ -365,7 +365,7 @@ Enable Low-latency HLS(LHLS). Adds #EXT-X-PREFETCH tag with current segment's UR Apple doesn't have an official spec for LHLS. Meanwhile hls.js player folks are trying to standardize a open LHLS spec. The draft spec is available in https://github.com/video-dev/hlsjs-rfcs/blob/lhls-spec/proposals/0001-lhls.… This option will also try to comply with the above open spec, till Apple's spec officially supports it. -Applicable only when @var{streaming} and @var{hls_playlist} options are enabled. +It enables @var{streaming} and @var{hls_playlist} options automatically. This is an experimental feature. @item ldash @var{ldash} diff --git a/libavformat/dashenc.c b/libavformat/dashenc.c index f9ec43689d..5faf06e11d 100644 --- a/libavformat/dashenc.c +++ b/libavformat/dashenc.c @@ -1396,13 +1396,13 @@ static int dash_init(AVFormatContext *s) } if (c->lhls && !c->streaming) { - av_log(s, AV_LOG_WARNING, "LHLS option will be ignored as streaming is not enabled\n"); - c->lhls = 0; + av_log(s, AV_LOG_WARNING, "Enabling streaming as LHLS is enabled\n"); + c->streaming = 1; } if (c->lhls && !c->hls_playlist) { - av_log(s, AV_LOG_WARNING, "LHLS option will be ignored as hls_playlist is not enabled\n"); - c->lhls = 0; + av_log(s, AV_LOG_INFO, "Enabling hls_playlist as LHLS is enabled\n"); + c->hls_playlist = 1; } if (c->ldash && !c->streaming) {

1 0

avformat/dashenc: enabling streaming automatically for ldash
by Zhao Zhili 05 Nov '21

05 Nov '21

ffmpeg | branch: master | Zhao Zhili <quinkblack(a)foxmail.com> | Thu Oct 21 16:15:30 2021 +0800| [f6b90d5fef0bd2878227ab073f3ddae53c2e2147] | committer: James Almer avformat/dashenc: enabling streaming automatically for ldash There is a little chance that user specified contradicted options like -streaming 0 -ldash 1, however, it's more likely that user didn't know or forgot to enable streaming for ldash. So enabling streaming automatically to make the feature easier to use, similar like enable FF_MOV_FLAG_FRAGMENT/EMPTY_MOOV/DEFAULT_BASE_MOOF and so on for FF_MOV_FLAG_CMAF. > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=f6b90d5fef0bd2878… --- libavformat/dashenc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/libavformat/dashenc.c b/libavformat/dashenc.c index 94e77c7b8c..f9ec43689d 100644 --- a/libavformat/dashenc.c +++ b/libavformat/dashenc.c @@ -1406,8 +1406,8 @@ static int dash_init(AVFormatContext *s) } if (c->ldash && !c->streaming) { - av_log(s, AV_LOG_WARNING, "LDash option will be ignored as streaming is not enabled\n"); - c->ldash = 0; + av_log(s, AV_LOG_WARNING, "Enabling streaming as LDash is enabled\n"); + c->streaming = 1; } if (c->target_latency && !c->streaming) {

1 0

lavf/mov: Change default to prefer TFDT time and allow for fallback to SIDX or TFDT
by Thilo Borgmann 05 Nov '21

05 Nov '21

ffmpeg | branch: master | Thilo Borgmann <thilo.borgmann(a)mail.de> | Fri Nov 5 16:11:59 2021 +0100| [c42d513ede6bc58b2cc7b0e47f90be27700843f8] | committer: Thilo Borgmann lavf/mov: Change default to prefer TFDT time and allow for fallback to SIDX or TFDT > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=c42d513ede6bc58b2… --- doc/demuxers.texi | 2 +- libavformat/mov.c | 42 ++++++++++++++++++++++++++++-------------- tests/ref/seek/extra-mp4 | 48 ++++++++++++++++++++++++------------------------ 3 files changed, 53 insertions(+), 39 deletions(-) diff --git a/doc/demuxers.texi b/doc/demuxers.texi index 1c9575b2e8..cab8a7072c 100644 --- a/doc/demuxers.texi +++ b/doc/demuxers.texi @@ -691,7 +691,7 @@ Don't use mfra box to set timestamps @item use_tfdt For fragmented input, set fragment's starting timestamp to @code{baseMediaDecodeTime} from the @code{tfdt} box. -Default is disabled, which will preferentially use the @code{earliest_presentation_time} from the @code{sidx} box. +Default is enabled, which will prefer to use the @code{tfdt} box to set DTS. Disable to use the @code{earliest_presentation_time} from the @code{sidx} box. In either case, the timestamp from the @code{mfra} box will be used if it's available and @code{use_mfra_for} is set to pts or dts. diff --git a/libavformat/mov.c b/libavformat/mov.c index 3fcb1dc908..8a910a3165 100644 --- a/libavformat/mov.c +++ b/libavformat/mov.c @@ -4828,20 +4828,34 @@ static int mov_read_trun(MOVContext *c, AVIOContext *pb, MOVAtom atom) dts = frag_stream_info->first_tfra_pts; av_log(c->fc, AV_LOG_DEBUG, "found mfra time %"PRId64 ", using it for dts\n", pts); - } else if (frag_stream_info->sidx_pts != AV_NOPTS_VALUE && !c->use_tfdt) { - // FIXME: sidx earliest_presentation_time is *PTS*, s.b. - // pts = frag_stream_info->sidx_pts; - dts = frag_stream_info->sidx_pts - sc->time_offset; - av_log(c->fc, AV_LOG_DEBUG, "found sidx time %"PRId64 - ", using it for pts\n", pts); - } else if (frag_stream_info->tfdt_dts != AV_NOPTS_VALUE) { - dts = frag_stream_info->tfdt_dts - sc->time_offset; - av_log(c->fc, AV_LOG_DEBUG, "found tfdt time %"PRId64 - ", using it for dts\n", dts); } else { - dts = sc->track_end - sc->time_offset; - av_log(c->fc, AV_LOG_DEBUG, "found track end time %"PRId64 - ", using it for dts\n", dts); + int has_tfdt = frag_stream_info->tfdt_dts != AV_NOPTS_VALUE; + int has_sidx = frag_stream_info->sidx_pts != AV_NOPTS_VALUE; + int fallback_tfdt = !c->use_tfdt && !has_sidx && has_tfdt; + int fallback_sidx = c->use_tfdt && !has_tfdt && has_sidx; + + if (fallback_sidx) { + av_log(c->fc, AV_LOG_DEBUG, "use_tfdt set but no tfdt found, using sidx instead\n"); + } + if (fallback_tfdt) { + av_log(c->fc, AV_LOG_DEBUG, "use_tfdt not set but no sidx found, using tfdt instead\n"); + } + + if (has_tfdt && c->use_tfdt || fallback_tfdt) { + dts = frag_stream_info->tfdt_dts - sc->time_offset; + av_log(c->fc, AV_LOG_DEBUG, "found tfdt time %"PRId64 + ", using it for dts\n", dts); + } else if (has_sidx && !c->use_tfdt || fallback_sidx) { + // FIXME: sidx earliest_presentation_time is *PTS*, s.b. + // pts = frag_stream_info->sidx_pts; + dts = frag_stream_info->sidx_pts - sc->time_offset; + av_log(c->fc, AV_LOG_DEBUG, "found sidx time %"PRId64 + ", using it for pts\n", pts); + } else { + dts = sc->track_end - sc->time_offset; + av_log(c->fc, AV_LOG_DEBUG, "found track end time %"PRId64 + ", using it for dts\n", dts); + } } } else { dts = sc->track_end - sc->time_offset; @@ -8533,7 +8547,7 @@ static const AVOption mov_options[] = { FLAGS, "use_mfra_for" }, {"pts", "pts", 0, AV_OPT_TYPE_CONST, {.i64 = FF_MOV_FLAG_MFRA_PTS}, 0, 0, FLAGS, "use_mfra_for" }, - {"use_tfdt", "use tfdt for fragment timestamps", OFFSET(use_tfdt), AV_OPT_TYPE_BOOL, {.i64 = 0}, + {"use_tfdt", "use tfdt for fragment timestamps", OFFSET(use_tfdt), AV_OPT_TYPE_BOOL, {.i64 = 1}, 0, 1, FLAGS}, { "export_all", "Export unrecognized metadata entries", OFFSET(export_all), AV_OPT_TYPE_BOOL, { .i64 = 0 }, 0, 1, .flags = FLAGS }, diff --git a/tests/ref/seek/extra-mp4 b/tests/ref/seek/extra-mp4 index c17ce4003c..836f7c74ba 100644 --- a/tests/ref/seek/extra-mp4 +++ b/tests/ref/seek/extra-mp4 @@ -23,10 +23,10 @@ ret: 0 st: 0 flags:0 dts: 126.666667 pts: 126.766667 pos:13428716 size: ret: 0 st: 0 flags:0 dts: 126.700000 pts: 126.700000 pos:13431630 size: 781 ret: 0 st: 0 flags:0 dts: 126.733333 pts: 126.733333 pos:13432411 size: 817 ret: 0 st:-1 flags:0 ts: 50.576668 -ret: 0 st: 0 flags:1 dts: 50.600000 pts: 50.633333 pos:5858254 size: 67903 -ret: 0 st: 0 flags:0 dts: 50.633333 pts: 50.733333 pos:5926157 size: 1307 -ret: 0 st: 0 flags:0 dts: 50.666667 pts: 50.666667 pos:5927464 size: 150 -ret: 0 st: 0 flags:0 dts: 50.700000 pts: 50.700000 pos:5927614 size: 176 +ret: 0 st: 0 flags:1 dts: 50.633333 pts: 50.666667 pos:5858254 size: 67903 +ret: 0 st: 0 flags:0 dts: 50.666667 pts: 50.766667 pos:5926157 size: 1307 +ret: 0 st: 0 flags:0 dts: 50.700000 pts: 50.700000 pos:5927464 size: 150 +ret: 0 st: 0 flags:0 dts: 50.733333 pts: 50.733333 pos:5927614 size: 176 ret: 0 st:-1 flags:1 ts: 153.470835 ret: 0 st: 0 flags:1 dts: 151.966667 pts: 152.000000 pos:15705355 size:146924 ret: 0 st: 0 flags:0 dts: 152.000000 pts: 152.100000 pos:15852279 size: 1355 @@ -43,10 +43,10 @@ ret: 0 st: 0 flags:0 dts: 0.000000 pts: 0.033333 pos: 1470 size: 24 ret: 0 st: 0 flags:0 dts: 0.033333 pts: 0.066667 pos: 1494 size: 6779 ret: 0 st: 0 flags:0 dts: 0.066667 pts: 0.100000 pos: 8273 size: 11041 ret: 0 st:-1 flags:0 ts: 102.153336 -ret: 0 st: 0 flags:1 dts: 104.066667 pts: 104.100000 pos:11116461 size:112929 -ret: 0 st: 0 flags:0 dts: 104.100000 pts: 104.133333 pos:11229390 size: 585 -ret: 0 st: 0 flags:0 dts: 104.133333 pts: 104.166667 pos:11229975 size: 797 -ret: 0 st: 0 flags:0 dts: 104.166667 pts: 104.200000 pos:11230772 size: 810 +ret: 0 st: 0 flags:1 dts: 104.100000 pts: 104.133333 pos:11116461 size:112929 +ret: 0 st: 0 flags:0 dts: 104.133333 pts: 104.166667 pos:11229390 size: 585 +ret: 0 st: 0 flags:0 dts: 104.166667 pts: 104.200000 pos:11229975 size: 797 +ret: 0 st: 0 flags:0 dts: 104.200000 pts: 104.233333 pos:11230772 size: 810 ret: 0 st:-1 flags:1 ts: 25.047503 ret: 0 st: 0 flags:1 dts: 20.233333 pts: 20.266667 pos:2223959 size: 51823 ret: 0 st: 0 flags:0 dts: 20.266667 pts: 20.300000 pos:2275782 size: 488 @@ -58,10 +58,10 @@ ret: 0 st: 0 flags:0 dts: 131.266667 pts: 131.366667 pos:13790182 size: ret: 0 st: 0 flags:0 dts: 131.300000 pts: 131.300000 pos:13792531 size: 571 ret: 0 st: 0 flags:0 dts: 131.333333 pts: 131.333333 pos:13793102 size: 1190 ret: 0 st: 0 flags:1 ts: 50.835833 -ret: 0 st: 0 flags:1 dts: 50.600000 pts: 50.633333 pos:5858254 size: 67903 -ret: 0 st: 0 flags:0 dts: 50.633333 pts: 50.733333 pos:5926157 size: 1307 -ret: 0 st: 0 flags:0 dts: 50.666667 pts: 50.666667 pos:5927464 size: 150 -ret: 0 st: 0 flags:0 dts: 50.700000 pts: 50.700000 pos:5927614 size: 176 +ret: 0 st: 0 flags:1 dts: 50.633333 pts: 50.666667 pos:5858254 size: 67903 +ret: 0 st: 0 flags:0 dts: 50.666667 pts: 50.766667 pos:5926157 size: 1307 +ret: 0 st: 0 flags:0 dts: 50.700000 pts: 50.700000 pos:5927464 size: 150 +ret: 0 st: 0 flags:0 dts: 50.733333 pts: 50.733333 pos:5927614 size: 176 ret: 0 st:-1 flags:0 ts: 153.730004 ret: 0 st: 0 flags:1 dts: 157.033333 pts: 157.066667 pos:16225365 size: 82738 ret: 0 st: 0 flags:0 dts: 157.066667 pts: 157.166667 pos:16308103 size: 2273 @@ -93,10 +93,10 @@ ret: 0 st: 0 flags:0 dts: 127.866667 pts: 127.966667 pos:13581454 size: ret: 0 st: 0 flags:0 dts: 127.900000 pts: 127.900000 pos:13584390 size: 451 ret: 0 st: 0 flags:0 dts: 127.933333 pts: 127.933333 pos:13584841 size: 537 ret: 0 st: 0 flags:0 ts: 51.095011 -ret: 0 st: 0 flags:1 dts: 52.033333 pts: 52.066667 pos:6028050 size:115809 -ret: 0 st: 0 flags:0 dts: 52.066667 pts: 52.166667 pos:6143859 size: 1620 -ret: 0 st: 0 flags:0 dts: 52.100000 pts: 52.100000 pos:6145479 size: 92 -ret: 0 st: 0 flags:0 dts: 52.133333 pts: 52.133333 pos:6145571 size: 533 +ret: 0 st: 0 flags:1 dts: 52.066667 pts: 52.100000 pos:6028050 size:115809 +ret: 0 st: 0 flags:0 dts: 52.100000 pts: 52.200000 pos:6143859 size: 1620 +ret: 0 st: 0 flags:0 dts: 52.133333 pts: 52.133333 pos:6145479 size: 92 +ret: 0 st: 0 flags:0 dts: 52.166667 pts: 52.166667 pos:6145571 size: 533 ret: 0 st: 0 flags:1 ts: 153.989178 ret: 0 st: 0 flags:1 dts: 153.466667 pts: 153.500000 pos:15867700 size: 96169 ret: 0 st: 0 flags:0 dts: 153.500000 pts: 153.533333 pos:15963869 size: 785 @@ -113,10 +113,10 @@ ret: 0 st: 0 flags:0 dts: 0.000000 pts: 0.033333 pos: 1470 size: 24 ret: 0 st: 0 flags:0 dts: 0.033333 pts: 0.066667 pos: 1494 size: 6779 ret: 0 st: 0 flags:0 dts: 0.066667 pts: 0.100000 pos: 8273 size: 11041 ret: 0 st: 0 flags:0 ts: 102.671678 -ret: 0 st: 0 flags:1 dts: 104.066667 pts: 104.100000 pos:11116461 size:112929 -ret: 0 st: 0 flags:0 dts: 104.100000 pts: 104.133333 pos:11229390 size: 585 -ret: 0 st: 0 flags:0 dts: 104.133333 pts: 104.166667 pos:11229975 size: 797 -ret: 0 st: 0 flags:0 dts: 104.166667 pts: 104.200000 pos:11230772 size: 810 +ret: 0 st: 0 flags:1 dts: 104.100000 pts: 104.133333 pos:11116461 size:112929 +ret: 0 st: 0 flags:0 dts: 104.133333 pts: 104.166667 pos:11229390 size: 585 +ret: 0 st: 0 flags:0 dts: 104.166667 pts: 104.200000 pos:11229975 size: 797 +ret: 0 st: 0 flags:0 dts: 104.200000 pts: 104.233333 pos:11230772 size: 810 ret: 0 st: 0 flags:1 ts: 25.565844 ret: 0 st: 0 flags:1 dts: 25.300000 pts: 25.333333 pos:2607246 size: 40273 ret: 0 st: 0 flags:0 dts: 25.333333 pts: 25.433333 pos:2647519 size: 2959 @@ -128,7 +128,7 @@ ret: 0 st: 0 flags:0 dts: 131.266667 pts: 131.366667 pos:13790182 size: ret: 0 st: 0 flags:0 dts: 131.300000 pts: 131.300000 pos:13792531 size: 571 ret: 0 st: 0 flags:0 dts: 131.333333 pts: 131.333333 pos:13793102 size: 1190 ret: 0 st:-1 flags:1 ts: 51.354175 -ret: 0 st: 0 flags:1 dts: 50.600000 pts: 50.633333 pos:5858254 size: 67903 -ret: 0 st: 0 flags:0 dts: 50.633333 pts: 50.733333 pos:5926157 size: 1307 -ret: 0 st: 0 flags:0 dts: 50.666667 pts: 50.666667 pos:5927464 size: 150 -ret: 0 st: 0 flags:0 dts: 50.700000 pts: 50.700000 pos:5927614 size: 176 +ret: 0 st: 0 flags:1 dts: 50.633333 pts: 50.666667 pos:5858254 size: 67903 +ret: 0 st: 0 flags:0 dts: 50.666667 pts: 50.766667 pos:5926157 size: 1307 +ret: 0 st: 0 flags:0 dts: 50.700000 pts: 50.700000 pos:5927464 size: 150 +ret: 0 st: 0 flags:0 dts: 50.733333 pts: 50.733333 pos:5927614 size: 176

1 0

avcodec/libx264: fix sei payload leaks on error
by James Almer 05 Nov '21

05 Nov '21

ffmpeg | branch: master | James Almer <jamrial(a)gmail.com> | Mon Nov 1 18:57:56 2021 -0300| [f6ab103bb5c2dd494620f7a28ae232efe497a4d1] | committer: James Almer avcodec/libx264: fix sei payload leaks on error Signed-off-by: James Almer <jamrial(a)gmail.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=f6ab103bb5c2dd494… --- libavcodec/libx264.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) diff --git a/libavcodec/libx264.c b/libavcodec/libx264.c index 21f434d06d..0766b4a950 100644 --- a/libavcodec/libx264.c +++ b/libavcodec/libx264.c @@ -293,6 +293,18 @@ static void reconfig_encoder(AVCodecContext *ctx, const AVFrame *frame) } } +static void free_picture(AVCodecContext *ctx) +{ + X264Context *x4 = ctx->priv_data; + x264_picture_t *pic = &x4->pic; + + for (int i = 0; i < pic->extra_sei.num_payloads; i++) + av_free(pic->extra_sei.payloads[i].payload); + av_freep(&pic->extra_sei.payloads); + av_freep(&pic->prop.quant_offsets); + pic->extra_sei.num_payloads = 0; +} + static int X264_frame(AVCodecContext *ctx, AVPacket *pkt, const AVFrame *frame, int *got_packet) { @@ -396,15 +408,17 @@ static int X264_frame(AVCodecContext *ctx, AVPacket *pkt, const AVFrame *frame, roi = (const AVRegionOfInterest*)sd->data; roi_size = roi->self_size; if (!roi_size || sd->size % roi_size != 0) { + free_picture(ctx); av_log(ctx, AV_LOG_ERROR, "Invalid AVRegionOfInterest.self_size.\n"); return AVERROR(EINVAL); } nb_rois = sd->size / roi_size; qoffsets = av_calloc(mbx * mby, sizeof(*qoffsets)); - if (!qoffsets) + if (!qoffsets) { + free_picture(ctx); return AVERROR(ENOMEM); - + } // This list must be iterated in reverse because the first // region in the list applies when regions overlap. for (int i = nb_rois - 1; i >= 0; i--) { @@ -420,6 +434,7 @@ static int X264_frame(AVCodecContext *ctx, AVPacket *pkt, const AVFrame *frame, if (roi->qoffset.den == 0) { av_free(qoffsets); + free_picture(ctx); av_log(ctx, AV_LOG_ERROR, "AVRegionOfInterest.qoffset.den must not be zero.\n"); return AVERROR(EINVAL); } @@ -452,7 +467,7 @@ static int X264_frame(AVCodecContext *ctx, AVPacket *pkt, const AVFrame *frame, continue; tmp = av_fast_realloc(sei->payloads, &sei_data_size, (sei->num_payloads + 1) * sizeof(*sei_payload)); if (!tmp) { - av_freep(&x4->pic.prop.quant_offsets); + free_picture(ctx); return AVERROR(ENOMEM); } sei->payloads = tmp; @@ -460,7 +475,7 @@ static int X264_frame(AVCodecContext *ctx, AVPacket *pkt, const AVFrame *frame, sei_payload = &sei->payloads[sei->num_payloads]; sei_payload->payload = av_memdup(side_data->data, side_data->size); if (!sei_payload->payload) { - av_freep(&x4->pic.prop.quant_offsets); + free_picture(ctx); return AVERROR(ENOMEM); } sei_payload->payload_size = side_data->size;

1 0

swscale/input: fix planar_rgb16_to_a for gbrap10be and gbrap12be formats
by Mark Reid 04 Nov '21

04 Nov '21

ffmpeg | branch: master | Mark Reid <mindmark(a)gmail.com> | Wed Nov 3 10:55:14 2021 -0700| [d2379bd6a03bc57eb9cc027a75f21086474422fe] | committer: Michael Niedermayer swscale/input: fix planar_rgb16_to_a for gbrap10be and gbrap12be formats Signed-off-by: Michael Niedermayer <michael(a)niedermayer.cc> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=d2379bd6a03bc57eb… --- libswscale/input.c | 2 +- tests/ref/fate/filter-pixfmts-scale | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/libswscale/input.c b/libswscale/input.c index 477dc3d6b2..336f957c8c 100644 --- a/libswscale/input.c +++ b/libswscale/input.c @@ -911,7 +911,7 @@ static void planar_rgb_to_uv(uint8_t *_dstU, uint8_t *_dstV, const uint8_t *src[ } #define rdpx(src) \ - is_be ? AV_RB16(src) : AV_RL16(src) + (is_be ? AV_RB16(src) : AV_RL16(src)) static av_always_inline void planar_rgb16_to_y(uint8_t *_dst, const uint8_t *_src[4], int width, int bpc, int is_be, int32_t *rgb2yuv) { diff --git a/tests/ref/fate/filter-pixfmts-scale b/tests/ref/fate/filter-pixfmts-scale index 07c4ff536d..1623e5c939 100644 --- a/tests/ref/fate/filter-pixfmts-scale +++ b/tests/ref/fate/filter-pixfmts-scale @@ -19,9 +19,9 @@ bgra d8316272bc3a360ef9dff3ecc84520a3 bgra64be 4e6a1b9f9c18b881c27d76611d45f737 bgra64le efeee0abcc658ebcff049d5e74d74943 gbrap 4a100f750ac846b34bfeef0d6893c3de -gbrap10be dc6aea3559ea4fcdda1ccc4f23d2f2fb +gbrap10be 50735fbc471a5ac5a6645c85881f3670 gbrap10le 6e1cba57029fdf0f9d46b5e5cd55112b -gbrap12be dbe3a662c016563529032cd4dfb80262 +gbrap12be 58170165829484b3db4a3b9165198987 gbrap12le 24f5ecb32435b73353517e017c165e31 gbrap16be 31968e6872a46e8174fb57f8920ed10d gbrap16le 8c6758f33671b673b6d30969fc05a23d

1 0

avfilter/scale_npp: add scale2ref_npp filter
by Roman Arzumanyan 03 Nov '21

03 Nov '21

ffmpeg | branch: master | Roman Arzumanyan <rarzumanyan(a)nvidia.com> | Mon Sep 6 15:25:51 2021 +0300| [08a501946f95f3a998000ee923aa7fcb35ec0d4e] | committer: Timo Rothenpieler avfilter/scale_npp: add scale2ref_npp filter Signed-off-by: Timo Rothenpieler <timo(a)rothenpieler.org> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=08a501946f95f3a99… --- configure | 1 + doc/filters.texi | 111 +++++++++ libavfilter/Makefile | 1 + libavfilter/allfilters.c | 1 + libavfilter/version.h | 2 +- libavfilter/vf_scale_npp.c | 544 +++++++++++++++++++++++++++++++++++++++++---- 6 files changed, 620 insertions(+), 40 deletions(-) diff --git a/configure b/configure index c4fb1b7260..c01aa480c7 100755 --- a/configure +++ b/configure @@ -3095,6 +3095,7 @@ v4l2_m2m_deps="linux_videodev2_h sem_timedwait" hwupload_cuda_filter_deps="ffnvcodec" scale_npp_filter_deps="ffnvcodec libnpp" +scale2ref_npp_filter_deps="ffnvcodec libnpp" scale_cuda_filter_deps="ffnvcodec" scale_cuda_filter_deps_any="cuda_nvcc cuda_llvm" thumbnail_cuda_filter_deps="ffnvcodec" diff --git a/doc/filters.texi b/doc/filters.texi index 62a580a245..b537e421be 100644 --- a/doc/filters.texi +++ b/doc/filters.texi @@ -18494,6 +18494,7 @@ scale_cuda=passthrough=0 @end example @end itemize +@anchor{scale_npp} @section scale_npp Use the NVIDIA Performance Primitives (libnpp) to perform scaling and/or pixel @@ -18570,6 +18571,61 @@ This option can be handy if you need to have a video fit within or exceed a defined resolution using @option{force_original_aspect_ratio} but also have encoder restrictions on width or height divisibility. +@item eval +Specify when to evaluate @var{width} and @var{height} expression. It accepts the following values: + +@table @samp +@item init +Only evaluate expressions once during the filter initialization or when a command is processed. + +@item frame +Evaluate expressions for each incoming frame. + +@end table + +@end table + +The values of the @option{w} and @option{h} options are expressions +containing the following constants: + +@table @var +@item in_w +@item in_h +The input width and height + +@item iw +@item ih +These are the same as @var{in_w} and @var{in_h}. + +@item out_w +@item out_h +The output (scaled) width and height + +@item ow +@item oh +These are the same as @var{out_w} and @var{out_h} + +@item a +The same as @var{iw} / @var{ih} + +@item sar +input sample aspect ratio + +@item dar +The input display aspect ratio. Calculated from @code{(iw / ih) * sar}. + +@item n +The (sequential) number of the input frame, starting from 0. +Only available with @code{eval=frame}. + +@item t +The presentation timestamp of the input frame, expressed as a number of +seconds. Only available with @code{eval=frame}. + +@item pos +The position (byte offset) of the frame in the input stream, or NaN if +this information is unavailable and/or meaningless (for example in case of synthetic video). +Only available with @code{eval=frame}. @end table @section scale2ref @@ -18645,6 +18701,61 @@ If the specified expression is not valid, it is kept at its current value. @end table +@section scale2ref_npp + +Use the NVIDIA Performance Primitives (libnpp) to scale (resize) the input +video, based on a reference video. + +See the @ref{scale_npp} filter for available options, scale2ref_npp supports the same +but uses the reference video instead of the main input as basis. scale2ref_npp +also supports the following additional constants for the @option{w} and +@option{h} options: + +@table @var +@item main_w +@item main_h +The main input video's width and height + +@item main_a +The same as @var{main_w} / @var{main_h} + +@item main_sar +The main input video's sample aspect ratio + +@item main_dar, mdar +The main input video's display aspect ratio. Calculated from +@code{(main_w / main_h) * main_sar}. + +@item main_n +The (sequential) number of the main input frame, starting from 0. +Only available with @code{eval=frame}. + +@item main_t +The presentation timestamp of the main input frame, expressed as a number of +seconds. Only available with @code{eval=frame}. + +@item main_pos +The position (byte offset) of the frame in the main input stream, or NaN if +this information is unavailable and/or meaningless (for example in case of synthetic video). +Only available with @code{eval=frame}. +@end table + +@subsection Examples + +@itemize +@item +Scale a subtitle stream (b) to match the main video (a) in size before overlaying +@example +'scale2ref_npp[b][a];[a][b]overlay_cuda' +@end example + +@item +Scale a logo to 1/10th the height of a video, while preserving its display aspect ratio. +@example +[logo-in][video-in]scale2ref_npp=w=oh*mdar:h=ih/10[logo-out][video-out] +@end example +@end itemize + @section scharr Apply scharr operator to input video stream. diff --git a/libavfilter/Makefile b/libavfilter/Makefile index 933d9628ea..552bd4e286 100644 --- a/libavfilter/Makefile +++ b/libavfilter/Makefile @@ -415,6 +415,7 @@ OBJS-$(CONFIG_SCALE_QSV_FILTER) += vf_scale_qsv.o OBJS-$(CONFIG_SCALE_VAAPI_FILTER) += vf_scale_vaapi.o scale_eval.o vaapi_vpp.o OBJS-$(CONFIG_SCALE_VULKAN_FILTER) += vf_scale_vulkan.o vulkan.o OBJS-$(CONFIG_SCALE2REF_FILTER) += vf_scale.o scale_eval.o +OBJS-$(CONFIG_SCALE2REF_NPP_FILTER) += vf_scale_npp.o scale_eval.o OBJS-$(CONFIG_SCDET_FILTER) += vf_scdet.o OBJS-$(CONFIG_SCHARR_FILTER) += vf_convolution.o OBJS-$(CONFIG_SCROLL_FILTER) += vf_scroll.o diff --git a/libavfilter/allfilters.c b/libavfilter/allfilters.c index 409ab5d3c4..667b6fc246 100644 --- a/libavfilter/allfilters.c +++ b/libavfilter/allfilters.c @@ -396,6 +396,7 @@ extern const AVFilter ff_vf_scale_qsv; extern const AVFilter ff_vf_scale_vaapi; extern const AVFilter ff_vf_scale_vulkan; extern const AVFilter ff_vf_scale2ref; +extern const AVFilter ff_vf_scale2ref_npp; extern const AVFilter ff_vf_scdet; extern const AVFilter ff_vf_scharr; extern const AVFilter ff_vf_scroll; diff --git a/libavfilter/version.h b/libavfilter/version.h index f6bb4fbe69..3bd3816698 100644 --- a/libavfilter/version.h +++ b/libavfilter/version.h @@ -31,7 +31,7 @@ #define LIBAVFILTER_VERSION_MAJOR 8 #define LIBAVFILTER_VERSION_MINOR 16 -#define LIBAVFILTER_VERSION_MICRO 100 +#define LIBAVFILTER_VERSION_MICRO 101 #define LIBAVFILTER_VERSION_INT AV_VERSION_INT(LIBAVFILTER_VERSION_MAJOR, \ diff --git a/libavfilter/vf_scale_npp.c b/libavfilter/vf_scale_npp.c index 8da335154c..6ce82e5302 100644 --- a/libavfilter/vf_scale_npp.c +++ b/libavfilter/vf_scale_npp.c @@ -25,13 +25,13 @@ #include <stdio.h> #include <string.h> -#include "libavutil/avstring.h" -#include "libavutil/common.h" #include "libavutil/hwcontext.h" #include "libavutil/hwcontext_cuda_internal.h" #include "libavutil/cuda_check.h" #include "libavutil/internal.h" #include "libavutil/opt.h" +#include "libavutil/parseutils.h" +#include "libavutil/eval.h" #include "libavutil/pixdesc.h" #include "avfilter.h" @@ -44,6 +44,7 @@ static const enum AVPixelFormat supported_formats[] = { AV_PIX_FMT_YUV420P, + AV_PIX_FMT_YUVA420P, AV_PIX_FMT_NV12, AV_PIX_FMT_YUV444P, }; @@ -67,12 +68,62 @@ typedef struct NPPScaleStageContext { struct { int width; int height; - } planes_in[3], planes_out[3]; + } planes_in[4], planes_out[4]; AVBufferRef *frames_ctx; AVFrame *frame; } NPPScaleStageContext; +static const char *const var_names[] = { + "in_w", "iw", + "in_h", "ih", + "out_w", "ow", + "out_h", "oh", + "a", + "sar", + "dar", + "n", + "t", + "pos", + "main_w", + "main_h", + "main_a", + "main_sar", + "main_dar", "mdar", + "main_n", + "main_t", + "main_pos", + NULL +}; + +enum var_name { + VAR_IN_W, VAR_IW, + VAR_IN_H, VAR_IH, + VAR_OUT_W, VAR_OW, + VAR_OUT_H, VAR_OH, + VAR_A, + VAR_SAR, + VAR_DAR, + VAR_N, + VAR_T, + VAR_POS, + VAR_S2R_MAIN_W, + VAR_S2R_MAIN_H, + VAR_S2R_MAIN_A, + VAR_S2R_MAIN_SAR, + VAR_S2R_MAIN_DAR, VAR_S2R_MDAR, + VAR_S2R_MAIN_N, + VAR_S2R_MAIN_T, + VAR_S2R_MAIN_POS, + VARS_NB +}; + +enum EvalMode { + EVAL_MODE_INIT, + EVAL_MODE_FRAME, + EVAL_MODE_NB +}; + typedef struct NPPScaleContext { const AVClass *class; @@ -102,35 +153,269 @@ typedef struct NPPScaleContext { int force_divisible_by; int interp_algo; + + char* size_str; + + AVExpr* w_pexpr; + AVExpr* h_pexpr; + + double var_values[VARS_NB]; + + int eval_mode; } NPPScaleContext; -static int nppscale_init(AVFilterContext *ctx) +const AVFilter ff_vf_scale2ref_npp; + +static int config_props(AVFilterLink *outlink); + +static int check_exprs(AVFilterContext* ctx) { - NPPScaleContext *s = ctx->priv; - int i; + NPPScaleContext* scale = ctx->priv; + unsigned vars_w[VARS_NB] = {0}, vars_h[VARS_NB] = {0}; + + if (!scale->w_pexpr && !scale->h_pexpr) + return AVERROR(EINVAL); + + if (scale->w_pexpr) + av_expr_count_vars(scale->w_pexpr, vars_w, VARS_NB); + if (scale->h_pexpr) + av_expr_count_vars(scale->h_pexpr, vars_h, VARS_NB); + + if (vars_w[VAR_OUT_W] || vars_w[VAR_OW]) { + av_log(ctx, AV_LOG_ERROR, "Width expression cannot be self-referencing: '%s'.\n", scale->w_expr); + return AVERROR(EINVAL); + } + + if (vars_h[VAR_OUT_H] || vars_h[VAR_OH]) { + av_log(ctx, AV_LOG_ERROR, "Height expression cannot be self-referencing: '%s'.\n", scale->h_expr); + return AVERROR(EINVAL); + } + + if ((vars_w[VAR_OUT_H] || vars_w[VAR_OH]) && + (vars_h[VAR_OUT_W] || vars_h[VAR_OW])) { + av_log(ctx, AV_LOG_WARNING, "Circular references detected for width '%s' and height '%s' - possibly invalid.\n", scale->w_expr, scale->h_expr); + } + + if (ctx->filter != &ff_vf_scale2ref_npp && + (vars_w[VAR_S2R_MAIN_W] || vars_h[VAR_S2R_MAIN_W] || + vars_w[VAR_S2R_MAIN_H] || vars_h[VAR_S2R_MAIN_H] || + vars_w[VAR_S2R_MAIN_A] || vars_h[VAR_S2R_MAIN_A] || + vars_w[VAR_S2R_MAIN_SAR] || vars_h[VAR_S2R_MAIN_SAR] || + vars_w[VAR_S2R_MAIN_DAR] || vars_h[VAR_S2R_MAIN_DAR] || + vars_w[VAR_S2R_MDAR] || vars_h[VAR_S2R_MDAR] || + vars_w[VAR_S2R_MAIN_N] || vars_h[VAR_S2R_MAIN_N] || + vars_w[VAR_S2R_MAIN_T] || vars_h[VAR_S2R_MAIN_T] || + vars_w[VAR_S2R_MAIN_POS] || vars_h[VAR_S2R_MAIN_POS])) { + av_log(ctx, AV_LOG_ERROR, "Expressions with scale2ref_npp variables are not valid in scale_npp filter.\n"); + return AVERROR(EINVAL); + } + + if (scale->eval_mode == EVAL_MODE_INIT && + (vars_w[VAR_N] || vars_h[VAR_N] || + vars_w[VAR_T] || vars_h[VAR_T] || + vars_w[VAR_POS] || vars_h[VAR_POS] || + vars_w[VAR_S2R_MAIN_N] || vars_h[VAR_S2R_MAIN_N] || + vars_w[VAR_S2R_MAIN_T] || vars_h[VAR_S2R_MAIN_T] || + vars_w[VAR_S2R_MAIN_POS] || vars_h[VAR_S2R_MAIN_POS]) ) { + av_log(ctx, AV_LOG_ERROR, "Expressions with frame variables 'n', 't', 'pos' are not valid in init eval_mode.\n"); + return AVERROR(EINVAL); + } + + return 0; +} + +static int nppscale_parse_expr(AVFilterContext* ctx, char* str_expr, + AVExpr** pexpr_ptr, const char* var, + const char* args) +{ + NPPScaleContext* scale = ctx->priv; + int ret, is_inited = 0; + char* old_str_expr = NULL; + AVExpr* old_pexpr = NULL; + + if (str_expr) { + old_str_expr = av_strdup(str_expr); + if (!old_str_expr) + return AVERROR(ENOMEM); + av_opt_set(scale, var, args, 0); + } + + if (*pexpr_ptr) { + old_pexpr = *pexpr_ptr; + *pexpr_ptr = NULL; + is_inited = 1; + } + + ret = av_expr_parse(pexpr_ptr, args, var_names, NULL, NULL, NULL, NULL, 0, + ctx); + if (ret < 0) { + av_log(ctx, AV_LOG_ERROR, "Cannot parse expression for %s: '%s'\n", var, + args); + goto revert; + } + + ret = check_exprs(ctx); + if (ret < 0) + goto revert; + + if (is_inited && (ret = config_props(ctx->outputs[0])) < 0) + goto revert; + + av_expr_free(old_pexpr); + old_pexpr = NULL; + av_freep(&old_str_expr); + + return 0; + +revert: + av_expr_free(*pexpr_ptr); + *pexpr_ptr = NULL; + if (old_str_expr) { + av_opt_set(scale, var, old_str_expr, 0); + av_free(old_str_expr); + } + if (old_pexpr) + *pexpr_ptr = old_pexpr; + + return ret; +} + +static av_cold int nppscale_init(AVFilterContext* ctx) +{ + NPPScaleContext* scale = ctx->priv; + int i, ret; - if (!strcmp(s->format_str, "same")) { - s->format = AV_PIX_FMT_NONE; + if (!strcmp(scale->format_str, "same")) { + scale->format = AV_PIX_FMT_NONE; } else { - s->format = av_get_pix_fmt(s->format_str); - if (s->format == AV_PIX_FMT_NONE) { - av_log(ctx, AV_LOG_ERROR, "Unrecognized pixel format: %s\n", s->format_str); + scale->format = av_get_pix_fmt(scale->format_str); + if (scale->format == AV_PIX_FMT_NONE) { + av_log(ctx, AV_LOG_ERROR, "Unrecognized pixel format: %s\n", scale->format_str); return AVERROR(EINVAL); } } - for (i = 0; i < FF_ARRAY_ELEMS(s->stages); i++) { - s->stages[i].frame = av_frame_alloc(); - if (!s->stages[i].frame) + if (scale->size_str && (scale->w_expr || scale->h_expr)) { + av_log(ctx, AV_LOG_ERROR, + "Size and width/height exprs cannot be set at the same time.\n"); + return AVERROR(EINVAL); + } + + if (scale->w_expr && !scale->h_expr) + FFSWAP(char*, scale->w_expr, scale->size_str); + + if (scale->size_str) { + char buf[32]; + ret = av_parse_video_size(&scale->w, &scale->h, scale->size_str); + if (0 > ret) { + av_log(ctx, AV_LOG_ERROR, "Invalid size '%s'\n", scale->size_str); + return ret; + } + + snprintf(buf, sizeof(buf) - 1, "%d", scale->w); + ret = av_opt_set(scale, "w", buf, 0); + if (ret < 0) + return ret; + + snprintf(buf, sizeof(buf) - 1, "%d", scale->h); + ret = av_opt_set(scale, "h", buf, 0); + if (ret < 0) + return ret; + } + + if (!scale->w_expr) { + ret = av_opt_set(scale, "w", "iw", 0); + if (ret < 0) + return ret; + } + + if (!scale->h_expr) { + ret = av_opt_set(scale, "h", "ih", 0); + if (ret < 0) + return ret; + } + + ret = nppscale_parse_expr(ctx, NULL, &scale->w_pexpr, "width", scale->w_expr); + if (ret < 0) + return ret; + + ret = nppscale_parse_expr(ctx, NULL, &scale->h_pexpr, "height", scale->h_expr); + if (ret < 0) + return ret; + + for (i = 0; i < FF_ARRAY_ELEMS(scale->stages); i++) { + scale->stages[i].frame = av_frame_alloc(); + if (!scale->stages[i].frame) return AVERROR(ENOMEM); } - s->tmp_frame = av_frame_alloc(); - if (!s->tmp_frame) + scale->tmp_frame = av_frame_alloc(); + if (!scale->tmp_frame) return AVERROR(ENOMEM); return 0; } +static int nppscale_eval_dimensions(AVFilterContext* ctx) +{ + NPPScaleContext* scale = ctx->priv; + const char scale2ref = ctx->filter == &ff_vf_scale2ref_npp; + const AVFilterLink* inlink = ctx->inputs[scale2ref ? 1 : 0]; + char* expr; + int eval_w, eval_h; + int ret; + double res; + + scale->var_values[VAR_IN_W] = scale->var_values[VAR_IW] = inlink->w; + scale->var_values[VAR_IN_H] = scale->var_values[VAR_IH] = inlink->h; + scale->var_values[VAR_OUT_W] = scale->var_values[VAR_OW] = NAN; + scale->var_values[VAR_OUT_H] = scale->var_values[VAR_OH] = NAN; + scale->var_values[VAR_A] = (double)inlink->w / inlink->h; + scale->var_values[VAR_SAR] = inlink->sample_aspect_ratio.num ? + (double)inlink->sample_aspect_ratio.num / inlink->sample_aspect_ratio.den : 1; + scale->var_values[VAR_DAR] = scale->var_values[VAR_A] * scale->var_values[VAR_SAR]; + + if (scale2ref) { + const AVFilterLink* main_link = ctx->inputs[0]; + + scale->var_values[VAR_S2R_MAIN_W] = main_link->w; + scale->var_values[VAR_S2R_MAIN_H] = main_link->h; + scale->var_values[VAR_S2R_MAIN_A] = (double)main_link->w / main_link->h; + scale->var_values[VAR_S2R_MAIN_SAR] = main_link->sample_aspect_ratio.num ? + (double)main_link->sample_aspect_ratio.num / main_link->sample_aspect_ratio.den : 1; + scale->var_values[VAR_S2R_MAIN_DAR] = scale->var_values[VAR_S2R_MDAR] = + scale->var_values[VAR_S2R_MAIN_A] * scale->var_values[VAR_S2R_MAIN_SAR]; + } + + res = av_expr_eval(scale->w_pexpr, scale->var_values, NULL); + eval_w = scale->var_values[VAR_OUT_W] = scale->var_values[VAR_OW] = (int)res == 0 ? inlink->w : (int)res; + + res = av_expr_eval(scale->h_pexpr, scale->var_values, NULL); + if (isnan(res)) { + expr = scale->h_expr; + ret = AVERROR(EINVAL); + goto fail; + } + eval_h = scale->var_values[VAR_OUT_H] = scale->var_values[VAR_OH] = (int)res == 0 ? inlink->h : (int)res; + + res = av_expr_eval(scale->w_pexpr, scale->var_values, NULL); + if (isnan(res)) { + expr = scale->w_expr; + ret = AVERROR(EINVAL); + goto fail; + } + eval_w = scale->var_values[VAR_OUT_W] = scale->var_values[VAR_OW] = (int)res == 0 ? inlink->w : (int)res; + + scale->w = eval_w; + scale->h = eval_h; + + return 0; + +fail: + av_log(ctx, AV_LOG_ERROR, "Error when evaluating the expression '%s'.\n", + expr); + return ret; +} + static void nppscale_uninit(AVFilterContext *ctx) { NPPScaleContext *s = ctx->priv; @@ -141,6 +426,10 @@ static void nppscale_uninit(AVFilterContext *ctx) av_buffer_unref(&s->stages[i].frames_ctx); } av_frame_free(&s->tmp_frame); + + av_expr_free(s->w_pexpr); + av_expr_free(s->h_pexpr); + s->w_pexpr = s->h_pexpr = NULL; } static int init_stage(NPPScaleStageContext *stage, AVBufferRef *device_ctx) @@ -164,6 +453,13 @@ static int init_stage(NPPScaleStageContext *stage, AVBufferRef *device_ctx) stage->planes_out[i].height = stage->planes_out[0].height >> out_sh; } + if (AV_PIX_FMT_YUVA420P == stage->in_fmt) { + stage->planes_in[3].width = stage->planes_in[0].width; + stage->planes_in[3].height = stage->planes_in[0].height; + stage->planes_out[3].width = stage->planes_out[0].width; + stage->planes_out[3].height = stage->planes_out[0].height; + } + out_ref = av_hwframe_ctx_alloc(device_ctx); if (!out_ref) return AVERROR(ENOMEM); @@ -326,31 +622,32 @@ static int init_processing_chain(AVFilterContext *ctx, int in_width, int in_heig return 0; } -static int nppscale_config_props(AVFilterLink *outlink) +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_npp ? + outlink->src->inputs[1] : + outlink->src->inputs[0]; NPPScaleContext *s = ctx->priv; - int w, h; int ret; - if ((ret = ff_scale_eval_dimensions(s, - s->w_expr, s->h_expr, - inlink, outlink, - &w, &h)) < 0) + if ((ret = nppscale_eval_dimensions(ctx)) < 0) goto fail; - ff_scale_adjust_dimensions(inlink, &w, &h, - s->force_original_aspect_ratio, s->force_divisible_by); + ff_scale_adjust_dimensions(inlink, &s->w, &s->h, + s->force_original_aspect_ratio, + s->force_divisible_by); - if (((int64_t)h * inlink->w) > INT_MAX || - ((int64_t)w * inlink->h) > INT_MAX) + if (s->w > INT_MAX || s->h > INT_MAX || + (s->h * inlink->w) > INT_MAX || + (s->w * inlink->h) > INT_MAX) av_log(ctx, AV_LOG_ERROR, "Rescaled value for width or height is too big.\n"); - outlink->w = w; - outlink->h = h; + outlink->w = s->w; + outlink->h = s->h; - ret = init_processing_chain(ctx, inlink->w, inlink->h, w, h); + ret = init_processing_chain(ctx, inlink0->w, inlink0->h, outlink->w, outlink->h); if (ret < 0) return ret; @@ -370,6 +667,22 @@ fail: return ret; } +static int config_props_ref(AVFilterLink *outlink) +{ + AVFilterLink *inlink = outlink->src->inputs[1]; + AVFilterContext *ctx = outlink->src; + + outlink->w = inlink->w; + outlink->h = inlink->h; + outlink->sample_aspect_ratio = inlink->sample_aspect_ratio; + outlink->time_base = inlink->time_base; + outlink->frame_rate = inlink->frame_rate; + + ctx->outputs[1]->hw_frames_ctx = av_buffer_ref(ctx->inputs[1]->hw_frames_ctx); + + return 0; +} + static int nppscale_deinterleave(AVFilterContext *ctx, NPPScaleStageContext *stage, AVFrame *out, AVFrame *in) { @@ -454,12 +767,71 @@ static int (*const nppscale_process[])(AVFilterContext *ctx, NPPScaleStageContex [STAGE_INTERLEAVE] = nppscale_interleave, }; -static int nppscale_scale(AVFilterContext *ctx, AVFrame *out, AVFrame *in) +static int nppscale_scale(AVFilterLink *link, AVFrame *out, AVFrame *in) { + AVFilterContext *ctx = link->dst; NPPScaleContext *s = ctx->priv; + AVFilterLink *outlink = ctx->outputs[0]; AVFrame *src = in; + char buf[32]; int i, ret, last_stage = -1; + int frame_changed; + + frame_changed = in->width != link->w || + in->height != link->h || + in->format != link->format || + in->sample_aspect_ratio.den != link->sample_aspect_ratio.den || + in->sample_aspect_ratio.num != link->sample_aspect_ratio.num; + + if (s->eval_mode == EVAL_MODE_FRAME || frame_changed) { + unsigned vars_w[VARS_NB] = { 0 }, vars_h[VARS_NB] = { 0 }; + + av_expr_count_vars(s->w_pexpr, vars_w, VARS_NB); + av_expr_count_vars(s->h_pexpr, vars_h, VARS_NB); + + if (s->eval_mode == EVAL_MODE_FRAME && !frame_changed && ctx->filter != &ff_vf_scale2ref_npp && + !(vars_w[VAR_N] || vars_w[VAR_T] || vars_w[VAR_POS]) && + !(vars_h[VAR_N] || vars_h[VAR_T] || vars_h[VAR_POS]) && + s->w && s->h) + goto scale; + + if (s->eval_mode == EVAL_MODE_INIT) { + snprintf(buf, sizeof(buf)-1, "%d", outlink->w); + av_opt_set(s, "w", buf, 0); + snprintf(buf, sizeof(buf)-1, "%d", outlink->h); + av_opt_set(s, "h", buf, 0); + + ret = nppscale_parse_expr(ctx, NULL, &s->w_pexpr, "width", s->w_expr); + if (ret < 0) + return ret; + + ret = nppscale_parse_expr(ctx, NULL, &s->h_pexpr, "height", s->h_expr); + if (ret < 0) + return ret; + } + + if (ctx->filter == &ff_vf_scale2ref_npp) { + s->var_values[VAR_S2R_MAIN_N] = link->frame_count_out; + s->var_values[VAR_S2R_MAIN_T] = TS2T(in->pts, link->time_base); + s->var_values[VAR_S2R_MAIN_POS] = in->pkt_pos == -1 ? NAN : in->pkt_pos; + } else { + s->var_values[VAR_N] = link->frame_count_out; + s->var_values[VAR_T] = TS2T(in->pts, link->time_base); + s->var_values[VAR_POS] = in->pkt_pos == -1 ? NAN : in->pkt_pos; + } + + link->format = in->format; + link->w = in->width; + link->h = in->height; + + link->sample_aspect_ratio.den = in->sample_aspect_ratio.den; + link->sample_aspect_ratio.num = in->sample_aspect_ratio.num; + if ((ret = config_props(outlink)) < 0) + return ret; + } + +scale: for (i = 0; i < FF_ARRAY_ELEMS(s->stages); i++) { if (!s->stages[i].stage_needed) continue; @@ -516,7 +888,7 @@ static int nppscale_filter_frame(AVFilterLink *link, AVFrame *in) if (ret < 0) goto fail; - ret = nppscale_scale(ctx, out, in); + ret = nppscale_scale(link, out, in); CHECK_CU(device_hwctx->internal->cuda_dl->cuCtxPopCurrent(&dummy)); if (ret < 0) @@ -535,12 +907,54 @@ fail: return ret; } +static int nppscale_filter_frame_ref(AVFilterLink *link, AVFrame *in) +{ + NPPScaleContext *scale = link->dst->priv; + AVFilterLink *outlink = link->dst->outputs[1]; + int frame_changed; + + frame_changed = in->width != link->w || + in->height != link->h || + in->format != link->format || + in->sample_aspect_ratio.den != link->sample_aspect_ratio.den || + in->sample_aspect_ratio.num != link->sample_aspect_ratio.num; + + if (frame_changed) { + link->format = in->format; + link->w = in->width; + link->h = in->height; + link->sample_aspect_ratio.num = in->sample_aspect_ratio.num; + link->sample_aspect_ratio.den = in->sample_aspect_ratio.den; + + config_props_ref(outlink); + } + + if (scale->eval_mode == EVAL_MODE_FRAME) { + scale->var_values[VAR_N] = link->frame_count_out; + scale->var_values[VAR_T] = TS2T(in->pts, link->time_base); + scale->var_values[VAR_POS] = in->pkt_pos == -1 ? NAN : in->pkt_pos; + } + + return ff_filter_frame(outlink, in); +} + +static int request_frame(AVFilterLink *outlink) +{ + return ff_request_frame(outlink->src->inputs[0]); +} + +static int request_frame_ref(AVFilterLink *outlink) +{ + return ff_request_frame(outlink->src->inputs[1]); +} + #define OFFSET(x) offsetof(NPPScaleContext, x) #define FLAGS (AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_VIDEO_PARAM) static const AVOption options[] = { - { "w", "Output video width", OFFSET(w_expr), AV_OPT_TYPE_STRING, { .str = "iw" }, .flags = FLAGS }, - { "h", "Output video height", OFFSET(h_expr), AV_OPT_TYPE_STRING, { .str = "ih" }, .flags = FLAGS }, + { "w", "Output video width", OFFSET(w_expr), AV_OPT_TYPE_STRING, .flags = FLAGS }, + { "h", "Output video height", OFFSET(h_expr), AV_OPT_TYPE_STRING, .flags = FLAGS }, { "format", "Output pixel format", OFFSET(format_str), AV_OPT_TYPE_STRING, { .str = "same" }, .flags = FLAGS }, + { "s", "Output video size", OFFSET(size_str), AV_OPT_TYPE_STRING, { .str = NULL }, .flags = FLAGS }, { "interp_algo", "Interpolation algorithm used for resizing", OFFSET(interp_algo), AV_OPT_TYPE_INT, { .i64 = NPPI_INTER_CUBIC }, 0, INT_MAX, FLAGS, "interp_algo" }, { "nn", "nearest neighbour", 0, AV_OPT_TYPE_CONST, { .i64 = NPPI_INTER_NN }, 0, 0, FLAGS, "interp_algo" }, @@ -551,11 +965,14 @@ static const AVOption options[] = { { "cubic2p_b05c03", "2-parameter cubic (B=1/2, C=3/10)", 0, AV_OPT_TYPE_CONST, { .i64 = NPPI_INTER_CUBIC2P_B05C03 }, 0, 0, FLAGS, "interp_algo" }, { "super", "supersampling", 0, AV_OPT_TYPE_CONST, { .i64 = NPPI_INTER_SUPER }, 0, 0, FLAGS, "interp_algo" }, { "lanczos", "Lanczos", 0, AV_OPT_TYPE_CONST, { .i64 = NPPI_INTER_LANCZOS }, 0, 0, FLAGS, "interp_algo" }, - { "force_original_aspect_ratio", "decrease or increase w/h if necessary to keep the original AR", OFFSET(force_original_aspect_ratio), AV_OPT_TYPE_INT, { .i64 = 0}, 0, 2, FLAGS, "force_oar" }, + { "force_original_aspect_ratio", "decrease or increase w/h if necessary to keep the original AR", OFFSET(force_original_aspect_ratio), AV_OPT_TYPE_INT, { .i64 = 0 }, 0, 2, FLAGS, "force_oar" }, { "disable", NULL, 0, AV_OPT_TYPE_CONST, {.i64 = 0 }, 0, 0, FLAGS, "force_oar" }, { "decrease", NULL, 0, AV_OPT_TYPE_CONST, {.i64 = 1 }, 0, 0, FLAGS, "force_oar" }, { "increase", NULL, 0, AV_OPT_TYPE_CONST, {.i64 = 2 }, 0, 0, FLAGS, "force_oar" }, - { "force_divisible_by", "enforce that the output resolution is divisible by a defined integer when force_original_aspect_ratio is used", OFFSET(force_divisible_by), AV_OPT_TYPE_INT, { .i64 = 1}, 1, 256, FLAGS }, + { "force_divisible_by", "enforce that the output resolution is divisible by a defined integer when force_original_aspect_ratio is used", OFFSET(force_divisible_by), AV_OPT_TYPE_INT, { .i64 = 1 }, 1, 256, FLAGS }, + { "eval", "specify when to evaluate expressions", OFFSET(eval_mode), AV_OPT_TYPE_INT, { .i64 = EVAL_MODE_INIT }, 0, EVAL_MODE_NB-1, FLAGS, "eval" }, + { "init", "eval expressions once during initialization", 0, AV_OPT_TYPE_CONST, { .i64 = EVAL_MODE_INIT }, 0, 0, FLAGS, "eval" }, + { "frame", "eval expressions during initialization and per-frame", 0, AV_OPT_TYPE_CONST, { .i64 = EVAL_MODE_FRAME }, 0, 0, FLAGS, "eval" }, { NULL }, }; @@ -564,6 +981,7 @@ static const AVClass nppscale_class = { .item_name = av_default_item_name, .option = options, .version = LIBAVUTIL_VERSION_INT, + .category = AV_CLASS_CATEGORY_FILTER, }; static const AVFilterPad nppscale_inputs[] = { @@ -571,15 +989,15 @@ static const AVFilterPad nppscale_inputs[] = { .name = "default", .type = AVMEDIA_TYPE_VIDEO, .filter_frame = nppscale_filter_frame, - }, + } }; static const AVFilterPad nppscale_outputs[] = { { .name = "default", .type = AVMEDIA_TYPE_VIDEO, - .config_props = nppscale_config_props, - }, + .config_props = config_props, + } }; const AVFilter ff_vf_scale_npp = { @@ -600,3 +1018,51 @@ const AVFilter ff_vf_scale_npp = { .flags_internal = FF_FILTER_FLAG_HWFRAME_AWARE, }; + +static const AVFilterPad nppscale2ref_inputs[] = { + { + .name = "default", + .type = AVMEDIA_TYPE_VIDEO, + .filter_frame = nppscale_filter_frame, + }, + { + .name = "ref", + .type = AVMEDIA_TYPE_VIDEO, + .filter_frame = nppscale_filter_frame_ref, + } +}; + +static const AVFilterPad nppscale2ref_outputs[] = { + { + .name = "default", + .type = AVMEDIA_TYPE_VIDEO, + .config_props = config_props, + .request_frame= request_frame, + }, + { + .name = "ref", + .type = AVMEDIA_TYPE_VIDEO, + .config_props = config_props_ref, + .request_frame= request_frame_ref, + } +}; + +const AVFilter ff_vf_scale2ref_npp = { + .name = "scale2ref_npp", + .description = NULL_IF_CONFIG_SMALL("NVIDIA Performance Primitives video " + "scaling and format conversion to the " + "given reference."), + + .init = nppscale_init, + .uninit = nppscale_uninit, + + .priv_size = sizeof(NPPScaleContext), + .priv_class = &nppscale_class, + + FILTER_INPUTS(nppscale2ref_inputs), + FILTER_OUTPUTS(nppscale2ref_outputs), + + FILTER_SINGLE_PIXFMT(AV_PIX_FMT_CUDA), + + .flags_internal = FF_FILTER_FLAG_HWFRAME_AWARE, +};

1 0

avformat/isom_tags: fix 'ipcm' with samplesize equal to 16
by Zhao Zhili 03 Nov '21

03 Nov '21

ffmpeg | branch: master | Zhao Zhili <quinkblack(a)foxmail.com> | Fri Oct 29 15:49:07 2021 +0800| [82e3251dd269bdf3c45b991b12dab1ce7561d542] | committer: Paul B Mahol avformat/isom_tags: fix 'ipcm' with samplesize equal to 16 Use PCM_S16 so the codec_id will be updated later according to bits_per_coded_sample. > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=82e3251dd269bdf3c… --- libavformat/isom_tags.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/libavformat/isom_tags.c b/libavformat/isom_tags.c index d0400b18fc..62e60470a8 100644 --- a/libavformat/isom_tags.c +++ b/libavformat/isom_tags.c @@ -312,10 +312,10 @@ const AVCodecTag ff_codec_movaudio_tags[] = { { AV_CODEC_ID_PCM_S16LE, MKTAG('s', 'o', 'w', 't') }, { AV_CODEC_ID_PCM_S16BE, MKTAG('l', 'p', 'c', 'm') }, { AV_CODEC_ID_PCM_S16LE, MKTAG('l', 'p', 'c', 'm') }, + { AV_CODEC_ID_PCM_S16BE, MKTAG('i', 'p', 'c', 'm') }, + { AV_CODEC_ID_PCM_S16LE, MKTAG('i', 'p', 'c', 'm') }, { AV_CODEC_ID_PCM_S24BE, MKTAG('i', 'n', '2', '4') }, { AV_CODEC_ID_PCM_S24LE, MKTAG('i', 'n', '2', '4') }, - { AV_CODEC_ID_PCM_S24BE, MKTAG('i', 'p', 'c', 'm') }, - { AV_CODEC_ID_PCM_S24LE, MKTAG('i', 'p', 'c', 'm') }, { AV_CODEC_ID_PCM_S32BE, MKTAG('i', 'n', '3', '2') }, { AV_CODEC_ID_PCM_S32LE, MKTAG('i', 'n', '3', '2') }, { AV_CODEC_ID_PCM_S8, MKTAG('s', 'o', 'w', 't') },

1 0

avformat/dashenc: Fix comparing double with 0
by Limin Wang 03 Nov '21

03 Nov '21

ffmpeg | branch: master | Limin Wang <lance.lmwang(a)gmail.com> | Sun Oct 10 22:39:48 2021 +0800| [f05559554c41306698aa98618b140f06775e4bcb] | committer: Limin Wang avformat/dashenc: Fix comparing double with 0 Signed-off-by: Limin Wang <lance.lmwang(a)gmail.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=f05559554c4130669… --- libavformat/dashenc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libavformat/dashenc.c b/libavformat/dashenc.c index 06bbf36c95..94e77c7b8c 100644 --- a/libavformat/dashenc.c +++ b/libavformat/dashenc.c @@ -551,7 +551,7 @@ static void write_hls_media_playlist(OutputStream *os, AVFormatContext *s, for (i = start_index; i < os->nb_segments; i++) { Segment *seg = os->segments[i]; - if (prog_date_time == 0) { + if (fabs(prog_date_time) < 1e-7) { if (os->nb_segments == 1) prog_date_time = c->start_time_s; else

1 0

avutil/parseutils: add qhd(Quad HD) or wqhd(Wide Quad HD) for 1440p
by Limin Wang 03 Nov '21

03 Nov '21

ffmpeg | branch: master | Limin Wang <lance.lmwang(a)gmail.com> | Tue Oct 26 16:52:52 2021 +0800| [8dc8c01d6c237546be7d50b9c40a1440f43d8619] | committer: Limin Wang avutil/parseutils: add qhd(Quad HD) or wqhd(Wide Quad HD) for 1440p Signed-off-by: Limin Wang <lance.lmwang(a)gmail.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=8dc8c01d6c237546b… --- libavutil/parseutils.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/libavutil/parseutils.c b/libavutil/parseutils.c index 7f678cd85a..19bbdde611 100644 --- a/libavutil/parseutils.c +++ b/libavutil/parseutils.c @@ -102,6 +102,7 @@ static const VideoSizeAbbr video_size_abbrs[] = { { "wsxga", 1600,1024 }, { "wuxga", 1920,1200 }, { "woxga", 2560,1600 }, + { "wqhd", 2560,1440 }, { "wqsxga", 3200,2048 }, { "wquxga", 3840,2400 }, { "whsxga", 6400,4096 }, @@ -111,6 +112,7 @@ static const VideoSizeAbbr video_size_abbrs[] = { { "hd480", 852, 480 }, { "hd720", 1280, 720 }, { "hd1080", 1920,1080 }, + { "qhd", 2560,1440 }, { "2k", 2048,1080 }, /* Digital Cinema System Specification */ { "2kdci", 2048,1080 }, { "2kflat", 1998,1080 },

1 0

avutil/hwcontext_videotoolbox: fix use of unknown builtin '__builtin_available'
by Limin Wang 03 Nov '21

03 Nov '21

ffmpeg | branch: master | Limin Wang <lance.lmwang(a)gmail.com> | Sun Oct 31 19:34:33 2021 +0800| [6cab5206b0ad94990c435cb7c5cf3b29675e0231] | committer: Limin Wang avutil/hwcontext_videotoolbox: fix use of unknown builtin '__builtin_available' OSX version: 10.11.6 Apple LLVM version 8.0.0 (clang-800.0.42.1) Target: x86_64-apple-darwin15.6.0 Signed-off-by: Limin Wang <lance.lmwang(a)gmail.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=6cab5206b0ad94990… --- configure | 8 ++++++ libavutil/hwcontext_videotoolbox.c | 54 +++++++++++++++++++++----------------- 2 files changed, 38 insertions(+), 24 deletions(-) diff --git a/configure b/configure index ede8f9777b..c4fb1b7260 100755 --- a/configure +++ b/configure @@ -2329,6 +2329,10 @@ TYPES_LIST=" kCVImageBufferTransferFunction_SMPTE_ST_2084_PQ kCVImageBufferTransferFunction_ITU_R_2100_HLG kCVImageBufferTransferFunction_Linear + kCVImageBufferYCbCrMatrix_ITU_R_2020 + kCVImageBufferColorPrimaries_ITU_R_2020 + kCVImageBufferTransferFunction_ITU_R_2020 + kCVImageBufferTransferFunction_SMPTE_ST_428_1 socklen_t struct_addrinfo struct_group_source_req @@ -6273,6 +6277,10 @@ enabled videotoolbox && { check_func_headers CoreVideo/CVImageBuffer.h kCVImageBufferTransferFunction_SMPTE_ST_2084_PQ "-framework CoreVideo" check_func_headers CoreVideo/CVImageBuffer.h kCVImageBufferTransferFunction_ITU_R_2100_HLG "-framework CoreVideo" check_func_headers CoreVideo/CVImageBuffer.h kCVImageBufferTransferFunction_Linear "-framework CoreVideo" + check_func_headers CoreVideo/CVImageBuffer.h kCVImageBufferYCbCrMatrix_ITU_R_2020 "-framework CoreVideo" + check_func_headers CoreVideo/CVImageBuffer.h kCVImageBufferColorPrimaries_ITU_R_2020 "-framework CoreVideo" + check_func_headers CoreVideo/CVImageBuffer.h kCVImageBufferTransferFunction_ITU_R_2020 "-framework CoreVideo" + check_func_headers CoreVideo/CVImageBuffer.h kCVImageBufferTransferFunction_SMPTE_ST_428_1 "-framework CoreVideo" } check_struct "sys/time.h sys/resource.h" "struct rusage" ru_maxrss diff --git a/libavutil/hwcontext_videotoolbox.c b/libavutil/hwcontext_videotoolbox.c index 58095a1fc9..25f4e17715 100644 --- a/libavutil/hwcontext_videotoolbox.c +++ b/libavutil/hwcontext_videotoolbox.c @@ -375,10 +375,11 @@ static int vt_pixbuf_set_colorspace(AVHWFramesContext *hwfc, switch (src->colorspace) { case AVCOL_SPC_BT2020_CL: case AVCOL_SPC_BT2020_NCL: - if (__builtin_available(macOS 10.11, *)) - colormatrix = kCVImageBufferYCbCrMatrix_ITU_R_2020; - else - colormatrix = CFSTR("ITU_R_2020"); +#if HAVE_KCVIMAGEBUFFERYCBCRMATRIX_ITU_R_2020 + colormatrix = kCVImageBufferYCbCrMatrix_ITU_R_2020; +#else + colormatrix = CFSTR("ITU_R_2020"); +#endif break; case AVCOL_SPC_BT470BG: case AVCOL_SPC_SMPTE170M: @@ -398,10 +399,11 @@ static int vt_pixbuf_set_colorspace(AVHWFramesContext *hwfc, switch (src->color_primaries) { case AVCOL_PRI_BT2020: - if (__builtin_available(macOS 10.11, *)) - colorpri = kCVImageBufferColorPrimaries_ITU_R_2020; - else - colorpri = CFSTR("ITU_R_2020"); +#if HAVE_KCVIMAGEBUFFERCOLORPRIMARIES_ITU_R_2020 + colorpri = kCVImageBufferColorPrimaries_ITU_R_2020; +#else + colorpri = CFSTR("ITU_R_2020"); +#endif break; case AVCOL_PRI_BT709: colorpri = kCVImageBufferColorPrimaries_ITU_R_709_2; @@ -420,17 +422,19 @@ static int vt_pixbuf_set_colorspace(AVHWFramesContext *hwfc, switch (src->color_trc) { case AVCOL_TRC_SMPTE2084: - if (__builtin_available(macOS 10.13, *)) - colortrc = kCVImageBufferTransferFunction_SMPTE_ST_2084_PQ; - else - colortrc = CFSTR("SMPTE_ST_2084_PQ"); +#if HAVE_KCVIMAGEBUFFERTRANSFERFUNCTION_SMPTE_ST_2084_PQ + colortrc = kCVImageBufferTransferFunction_SMPTE_ST_2084_PQ; +#else + colortrc = CFSTR("SMPTE_ST_2084_PQ"); +#endif break; case AVCOL_TRC_BT2020_10: case AVCOL_TRC_BT2020_12: - if (__builtin_available(macOS 10.11, *)) - colortrc = kCVImageBufferTransferFunction_ITU_R_2020; - else - colortrc = CFSTR("ITU_R_2020"); +#if HAVE_KCVIMAGEBUFFERTRANSFERFUNCTION_ITU_R_2020 + colortrc = kCVImageBufferTransferFunction_ITU_R_2020; +#else + colortrc = CFSTR("ITU_R_2020"); +#endif break; case AVCOL_TRC_BT709: colortrc = kCVImageBufferTransferFunction_ITU_R_709_2; @@ -439,16 +443,18 @@ static int vt_pixbuf_set_colorspace(AVHWFramesContext *hwfc, colortrc = kCVImageBufferTransferFunction_SMPTE_240M_1995; break; case AVCOL_TRC_SMPTE428: - if (__builtin_available(macOS 10.12, *)) - colortrc = kCVImageBufferTransferFunction_SMPTE_ST_428_1; - else - colortrc = CFSTR("SMPTE_ST_428_1"); +#if HAVE_KCVIMAGEBUFFERTRANSFERFUNCTION_SMPTE_ST_428_1 + colortrc = kCVImageBufferTransferFunction_SMPTE_ST_428_1; +#else + colortrc = CFSTR("SMPTE_ST_428_1"); +#endif break; case AVCOL_TRC_ARIB_STD_B67: - if (__builtin_available(macOS 10.13, *)) - colortrc = kCVImageBufferTransferFunction_ITU_R_2100_HLG; - else - colortrc = CFSTR("ITU_R_2100_HLG"); +#if HAVE_KCVIMAGEBUFFERTRANSFERFUNCTION_ITU_R_2100_HLG + colortrc = kCVImageBufferTransferFunction_ITU_R_2100_HLG; +#else + colortrc = CFSTR("ITU_R_2100_HLG"); +#endif break; case AVCOL_TRC_GAMMA22: gamma = 2.2;

1 0