June 2021 - ffmpeg-cvslog - lists.ffmpeg.org

doc/muxers: note atomic_writing in image2
by Gyan Doshi 30 Jun '21

30 Jun '21

ffmpeg | branch: master | Gyan Doshi <ffmpeg(a)gyani.pro> | Wed Jun 30 09:52:09 2021 +0530| [de8e6e67e7523e48bb27ac224a0b446df05e1640] | committer: Gyan Doshi doc/muxers: note atomic_writing in image2 Fixes #9308 > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=de8e6e67e7523e48b… --- doc/muxers.texi | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/doc/muxers.texi b/doc/muxers.texi index e77055e7ef..0972bbfd5c 100644 --- a/doc/muxers.texi +++ b/doc/muxers.texi @@ -1419,6 +1419,10 @@ overwritten with new images. Default value is 0. If set to 1, expand the filename with date and time information from @code{strftime()}. Default value is 0. +@item atomic_writing +Write output to a temporary file, which is renamed to target filename once +writing is completed. Default is disabled. + @item protocol_opts @var{options_list} Set protocol options as a :-separated list of key=value parameters. Values containing the @code{:} special character must be escaped.

1 0

doc: remove duplicate @end command
by James Almer 30 Jun '21

30 Jun '21

ffmpeg | branch: master | James Almer <jamrial(a)gmail.com> | Tue Jun 29 22:27:15 2021 -0300| [91004ed3ec3934c19db405ea818ce2ba73a8225e] | committer: James Almer doc: remove duplicate @end command Fixes regression since e11fd47f8df2631db9da14b22d34e3c390d91ba8 Signed-off-by: James Almer <jamrial(a)gmail.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=91004ed3ec3934c19… --- doc/filters.texi | 1 - 1 file changed, 1 deletion(-) diff --git a/doc/filters.texi b/doc/filters.texi index 13236965ce..eaf23e3736 100644 --- a/doc/filters.texi +++ b/doc/filters.texi @@ -20975,7 +20975,6 @@ If diagonal field of view is set it overrides horizontal and vertical field of v @item octahedron Octahedron projection. -@end table @item cylindricalea Cylindrical Equal Area projection.

1 0

avfilter/vf_v360: add cylindrical equal area format
by Paul B Mahol 29 Jun '21

29 Jun '21

ffmpeg | branch: master | Paul B Mahol <onemda(a)gmail.com> | Wed Jun 30 00:12:41 2021 +0200| [e11fd47f8df2631db9da14b22d34e3c390d91ba8] | committer: Paul B Mahol avfilter/vf_v360: add cylindrical equal area format > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=e11fd47f8df2631db… --- doc/filters.texi | 4 ++ libavfilter/v360.h | 1 + libavfilter/vf_v360.c | 124 ++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 129 insertions(+) diff --git a/doc/filters.texi b/doc/filters.texi index 67ad228d8b..13236965ce 100644 --- a/doc/filters.texi +++ b/doc/filters.texi @@ -20977,6 +20977,10 @@ If diagonal field of view is set it overrides horizontal and vertical field of v Octahedron projection. @end table +@item cylindricalea +Cylindrical Equal Area projection. +@end table + @item interp Set interpolation method.@* @i{Note: more complex interpolation methods require much more memory to run.} diff --git a/libavfilter/v360.h b/libavfilter/v360.h index 87770664a3..b8ade2591c 100644 --- a/libavfilter/v360.h +++ b/libavfilter/v360.h @@ -54,6 +54,7 @@ enum Projections { EQUISOLID, ORTHOGRAPHIC, OCTAHEDRON, + CYLINDRICALEA, NB_PROJECTIONS, }; diff --git a/libavfilter/vf_v360.c b/libavfilter/vf_v360.c index c47a4015e8..0c47883d4d 100644 --- a/libavfilter/vf_v360.c +++ b/libavfilter/vf_v360.c @@ -84,6 +84,7 @@ static const AVOption v360_options[] = { { "equisolid", "equisolid", 0, AV_OPT_TYPE_CONST, {.i64=EQUISOLID}, 0, 0, FLAGS, "in" }, { "og", "orthographic", 0, AV_OPT_TYPE_CONST, {.i64=ORTHOGRAPHIC}, 0, 0, FLAGS, "in" }, {"octahedron", "octahedron", 0, AV_OPT_TYPE_CONST, {.i64=OCTAHEDRON}, 0, 0, FLAGS, "in" }, + {"cylindricalea", "cylindrical equal area", 0, AV_OPT_TYPE_CONST, {.i64=CYLINDRICALEA}, 0, 0, FLAGS, "in" }, { "output", "set output projection", OFFSET(out), AV_OPT_TYPE_INT, {.i64=CUBEMAP_3_2}, 0, NB_PROJECTIONS-1, FLAGS, "out" }, { "e", "equirectangular", 0, AV_OPT_TYPE_CONST, {.i64=EQUIRECTANGULAR}, 0, 0, FLAGS, "out" }, { "equirect", "equirectangular", 0, AV_OPT_TYPE_CONST, {.i64=EQUIRECTANGULAR}, 0, 0, FLAGS, "out" }, @@ -114,6 +115,7 @@ static const AVOption v360_options[] = { { "equisolid", "equisolid", 0, AV_OPT_TYPE_CONST, {.i64=EQUISOLID}, 0, 0, FLAGS, "out" }, { "og", "orthographic", 0, AV_OPT_TYPE_CONST, {.i64=ORTHOGRAPHIC}, 0, 0, FLAGS, "out" }, {"octahedron", "octahedron", 0, AV_OPT_TYPE_CONST, {.i64=OCTAHEDRON}, 0, 0, FLAGS, "out" }, + {"cylindricalea", "cylindrical equal area", 0, AV_OPT_TYPE_CONST, {.i64=CYLINDRICALEA}, 0, 0, FLAGS, "out" }, { "interp", "set interpolation method", OFFSET(interp), AV_OPT_TYPE_INT, {.i64=BILINEAR}, 0, NB_INTERP_METHODS-1, FLAGS, "interp" }, { "near", "nearest neighbour", 0, AV_OPT_TYPE_CONST, {.i64=NEAREST}, 0, 0, FLAGS, "interp" }, { "nearest", "nearest neighbour", 0, AV_OPT_TYPE_CONST, {.i64=NEAREST}, 0, 0, FLAGS, "interp" }, @@ -3136,6 +3138,116 @@ static int xyz_to_cylindrical(const V360Context *s, return visible; } +/** + * Prepare data for processing cylindrical equal area output format. + * + * @param ctx filter context + * + * @return error code + */ +static int prepare_cylindricalea_out(AVFilterContext *ctx) +{ + V360Context *s = ctx->priv; + + s->flat_range[0] = s->h_fov * M_PI / 360.f; + s->flat_range[1] = s->v_fov / 180.f; + + return 0; +} + +/** + * Prepare data for processing cylindrical equal area input format. + * + * @param ctx filter context + * + * @return error code + */ +static int prepare_cylindricalea_in(AVFilterContext *ctx) +{ + V360Context *s = ctx->priv; + + s->iflat_range[0] = M_PI * s->ih_fov / 360.f; + s->iflat_range[1] = s->iv_fov / 180.f; + + return 0; +} + +/** + * Calculate 3D coordinates on sphere for corresponding frame position in cylindrical equal area format. + * + * @param s filter private context + * @param i horizontal position on frame [0, width) + * @param j vertical position on frame [0, height) + * @param width frame width + * @param height frame height + * @param vec coordinates on sphere + */ +static int cylindricalea_to_xyz(const V360Context *s, + int i, int j, int width, int height, + float *vec) +{ + const float uf = s->flat_range[0] * ((2.f * i + 1.f) / width - 1.f); + const float vf = s->flat_range[1] * ((2.f * j + 1.f) / height - 1.f); + + const float phi = uf; + const float theta = asinf(vf); + + const float sin_phi = sinf(phi); + const float cos_phi = cosf(phi); + const float sin_theta = sinf(theta); + const float cos_theta = cosf(theta); + + vec[0] = cos_theta * sin_phi; + vec[1] = sin_theta; + vec[2] = cos_theta * cos_phi; + + normalize_vector(vec); + + return 1; +} + +/** + * Calculate frame position in cylindrical equal area format for corresponding 3D coordinates on sphere. + * + * @param s filter private context + * @param vec coordinates on sphere + * @param width frame width + * @param height frame height + * @param us horizontal coordinates for interpolation window + * @param vs vertical coordinates for interpolation window + * @param du horizontal relative coordinate + * @param dv vertical relative coordinate + */ +static int xyz_to_cylindricalea(const V360Context *s, + const float *vec, int width, int height, + int16_t us[4][4], int16_t vs[4][4], float *du, float *dv) +{ + const float phi = atan2f(vec[0], vec[2]) / s->iflat_range[0]; + const float theta = asinf(vec[1]); + + const float uf = (phi + 1.f) * (width - 1) / 2.f; + const float vf = (sinf(theta) / s->iflat_range[1] + 1.f) * height / 2.f; + + const int ui = floorf(uf); + const int vi = floorf(vf); + + const int visible = vi >= 0 && vi < height && ui >= 0 && ui < width && + theta <= M_PI * s->iv_fov / 180.f && + theta >= -M_PI * s->iv_fov / 180.f; + + *du = uf - ui; + *dv = vf - vi; + + for (int i = 0; i < 4; i++) { + for (int j = 0; j < 4; j++) { + us[i][j] = visible ? av_clip(ui + j - 1, 0, width - 1) : 0; + vs[i][j] = visible ? av_clip(vi + i - 1, 0, height - 1) : 0; + } + } + + return visible; +} + /** * Calculate 3D coordinates on sphere for corresponding frame position in perspective format. * @@ -4448,6 +4560,12 @@ static int config_output(AVFilterLink *outlink) wf = w; hf = h * 2.f; break; + case CYLINDRICALEA: + s->in_transform = xyz_to_cylindricalea; + err = prepare_cylindricalea_in(ctx); + wf = w; + hf = h; + break; case TETRAHEDRON: s->in_transform = xyz_to_tetrahedron; err = 0; @@ -4596,6 +4714,12 @@ static int config_output(AVFilterLink *outlink) w = lrintf(wf); h = lrintf(hf * 0.5f); break; + case CYLINDRICALEA: + s->out_transform = cylindricalea_to_xyz; + prepare_out = prepare_cylindricalea_out; + w = lrintf(wf); + h = lrintf(hf); + break; case PERSPECTIVE: s->out_transform = perspective_to_xyz; prepare_out = NULL;

1 0

avcodec/cpia: Fix missing src_size update
by Michael Niedermayer 29 Jun '21

29 Jun '21

ffmpeg | branch: master | Michael Niedermayer <michael(a)niedermayer.cc> | Mon Jun 21 22:59:04 2021 +0200| [cea05864e65db9a2dc8af82b2c63fb8f03c5f876] | committer: Michael Niedermayer avcodec/cpia: Fix missing src_size update Fixes: out of array read Fixes: 35210/clusterfuzz-testcase-minimized-ffmpeg_AV_CODEC_ID_CPIA_fuzzer-5669199688105984 Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg Signed-off-by: Michael Niedermayer <michael(a)niedermayer.cc> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=cea05864e65db9a2d… --- libavcodec/cpia.c | 1 + 1 file changed, 1 insertion(+) diff --git a/libavcodec/cpia.c b/libavcodec/cpia.c index d88bd1aae7..a2ae16ec2c 100644 --- a/libavcodec/cpia.c +++ b/libavcodec/cpia.c @@ -111,6 +111,7 @@ static int cpia_decode_frame(AVCodecContext *avctx, // Read line length, two byte little endian linelength = AV_RL16(src); src += 2; + src_size -= 2; if (src_size < linelength) { frame->decode_error_flags = FF_DECODE_ERROR_INVALID_BITSTREAM;

1 0

avcodec/exr: Better size checks
by Michael Niedermayer 29 Jun '21

29 Jun '21

ffmpeg | branch: master | Michael Niedermayer <michael(a)niedermayer.cc> | Mon Jun 21 22:15:47 2021 +0200| [18b0dd07384b2987f24a4d0ba7600fde2787472a] | committer: Michael Niedermayer avcodec/exr: Better size checks Fixes: signed integer overflow: 3530839700044513368 + 8386093932303352321 cannot be represented in type 'long long' Fixes: 35182/clusterfuzz-testcase-minimized-ffmpeg_AV_CODEC_ID_EXR_fuzzer-5398383270428672 Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg Signed-off-by: Michael Niedermayer <michael(a)niedermayer.cc> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=18b0dd07384b2987f… --- libavcodec/exr.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libavcodec/exr.c b/libavcodec/exr.c index 4648ed7d62..e7387ffd66 100644 --- a/libavcodec/exr.c +++ b/libavcodec/exr.c @@ -1014,7 +1014,7 @@ static int dwa_uncompress(EXRContext *s, const uint8_t *src, int compressed_size dc_count = AV_RL64(src + 72); ac_compression = AV_RL64(src + 80); - if (compressed_size < 88LL + lo_size + ac_size + dc_size + rle_csize) + if (compressed_size < (uint64_t)(lo_size | ac_size | dc_size | rle_csize) || compressed_size < 88LL + lo_size + ac_size + dc_size + rle_csize) return AVERROR_INVALIDDATA; bytestream2_init(&gb, src + 88, compressed_size - 88);

1 0

avcodec/clearvideo: Check tile_size to be not too large
by Michael Niedermayer 29 Jun '21

29 Jun '21

ffmpeg | branch: master | Michael Niedermayer <michael(a)niedermayer.cc> | Mon Jun 21 21:02:39 2021 +0200| [11fac9613e6a340d4d9968e2d8a43c3726ab57d3] | committer: Michael Niedermayer avcodec/clearvideo: Check tile_size to be not too large Fixes: left shift of 1 by 31 places cannot be represented in type 'int' Fixes: 35023/clusterfuzz-testcase-minimized-ffmpeg_AV_CODEC_ID_CLEARVIDEO_fuzzer-6740166587842560 Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg Signed-off-by: Michael Niedermayer <michael(a)niedermayer.cc> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=11fac9613e6a340d4… --- libavcodec/clearvideo.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/libavcodec/clearvideo.c b/libavcodec/clearvideo.c index 5c79376c64..5ed8ac71dc 100644 --- a/libavcodec/clearvideo.c +++ b/libavcodec/clearvideo.c @@ -722,8 +722,8 @@ static av_cold int clv_decode_init(AVCodecContext *avctx) } c->tile_shift = av_log2(c->tile_size); - if (1U << c->tile_shift != c->tile_size || c->tile_shift < 1) { - av_log(avctx, AV_LOG_ERROR, "Tile size: %d, is not power of 2 > 1\n", c->tile_size); + if (1U << c->tile_shift != c->tile_size || c->tile_shift < 1 || c->tile_shift > 30) { + av_log(avctx, AV_LOG_ERROR, "Tile size: %d, is not power of 2 > 1 and < 2^31\n", c->tile_size); return AVERROR_INVALIDDATA; }

1 0

avcodec/utils: Use 64bit for intermediate in AV_CODEC_ID_ADPCM_THP* duration calculation
by Michael Niedermayer 29 Jun '21

29 Jun '21

ffmpeg | branch: master | Michael Niedermayer <michael(a)niedermayer.cc> | Thu Jun 24 20:00:05 2021 +0200| [00ae9b77ef757f82660b4b3d2f490374a4f209fd] | committer: Michael Niedermayer avcodec/utils: Use 64bit for intermediate in AV_CODEC_ID_ADPCM_THP* duration calculation Fixes: signed integer overflow: 486539264 * 14 cannot be represented in type 'int' Fixes: 35281/clusterfuzz-testcase-minimized-ffmpeg_dem_RSD_fuzzer-6068262742917120 Found-by: continuous fuzzing process https://github.com/google/oss-fuzz/tree/master/projects/ffmpeg Signed-off-by: Michael Niedermayer <michael(a)niedermayer.cc> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=00ae9b77ef757f826… --- libavcodec/utils.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/libavcodec/utils.c b/libavcodec/utils.c index 342709353f..88e88bc958 100644 --- a/libavcodec/utils.c +++ b/libavcodec/utils.c @@ -712,7 +712,7 @@ static int get_audio_frame_duration(enum AVCodecID id, int sr, int ch, int ba, case AV_CODEC_ID_ADPCM_THP: case AV_CODEC_ID_ADPCM_THP_LE: if (extradata) - return frame_bytes * 14 / (8 * ch); + return frame_bytes * 14LL / (8 * ch); break; case AV_CODEC_ID_ADPCM_XA: return (frame_bytes / 128) * 224 / ch;

1 0

avcodec/h264_metadata_bsf: Allow zeroing constraint_set4_flag and constraint_set5_flag
by Derek Buitenhuis 29 Jun '21

29 Jun '21

ffmpeg | branch: master | Derek Buitenhuis <derek.buitenhuis(a)gmail.com> | Wed Jun 23 17:12:43 2021 +0100| [d70dde2712bbead523004d8294ff1a0fdeab480b] | committer: Derek Buitenhuis avcodec/h264_metadata_bsf: Allow zeroing constraint_set4_flag and constraint_set5_flag These bits are reserved in earlier versions of the H.264 spec, and some poor hardware decoders require they are zero. Thus, it is useful to be able to zero these on streams that may have them set. The result is still a valid H.264 bitstream. Signed-off-by: Derek Buitenhuis <derek.buitenhuis(a)gmail.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=d70dde2712bbead52… --- doc/bitstream_filters.texi | 5 +++++ libavcodec/h264_metadata_bsf.c | 8 ++++++++ libavcodec/version.h | 2 +- 3 files changed, 14 insertions(+), 1 deletion(-) diff --git a/doc/bitstream_filters.texi b/doc/bitstream_filters.texi index 60e729484d..e3c56f1887 100644 --- a/doc/bitstream_filters.texi +++ b/doc/bitstream_filters.texi @@ -253,6 +253,11 @@ Set whether the stream has fixed framerate - typically this indicates that the framerate is exactly half the tick rate, but the exact meaning is dependent on interlacing and the picture structure (see H.264 section E.2.1 and table E-6). +@item zero_new_constraint_set_flags +Zero constraint_set4_flag and constraint_set5_flag in the SPS. These +bits were reserved in a previous version of the H.264 spec, and thus +some hardware decoders require these to be zero. The result of zeroing +this is still a valid bitstream. @item crop_left @item crop_right diff --git a/libavcodec/h264_metadata_bsf.c b/libavcodec/h264_metadata_bsf.c index ef74cba560..452a8ec5dc 100644 --- a/libavcodec/h264_metadata_bsf.c +++ b/libavcodec/h264_metadata_bsf.c @@ -61,6 +61,7 @@ typedef struct H264MetadataContext { AVRational tick_rate; int fixed_frame_rate_flag; + int zero_new_constraint_set_flags; int crop_left; int crop_right; @@ -228,6 +229,10 @@ static int h264_metadata_update_sps(AVBSFContext *bsf, need_vui = 1; } SET_VUI_FIELD(fixed_frame_rate_flag); + if (ctx->zero_new_constraint_set_flags) { + sps->constraint_set4_flag = 0; + sps->constraint_set5_flag = 0; + } if (sps->separate_colour_plane_flag || sps->chroma_format_idc == 0) { crop_unit_x = 1; @@ -618,6 +623,9 @@ static const AVOption h264_metadata_options[] = { { "fixed_frame_rate_flag", "Set VUI fixed frame rate flag", OFFSET(fixed_frame_rate_flag), AV_OPT_TYPE_INT, { .i64 = -1 }, -1, 1, FLAGS }, + { "zero_new_constraint_set_flags", "Set constraint_set4_flag / constraint_set5_flag to zero", + OFFSET(zero_new_constraint_set_flags), AV_OPT_TYPE_BOOL, + { .i64 = 0 }, 0, 1, FLAGS }, { "crop_left", "Set left border crop offset", OFFSET(crop_left), AV_OPT_TYPE_INT, diff --git a/libavcodec/version.h b/libavcodec/version.h index 1288cecebe..2a420a7e28 100644 --- a/libavcodec/version.h +++ b/libavcodec/version.h @@ -28,7 +28,7 @@ #include "libavutil/version.h" #define LIBAVCODEC_VERSION_MAJOR 59 -#define LIBAVCODEC_VERSION_MINOR 2 +#define LIBAVCODEC_VERSION_MINOR 3 #define LIBAVCODEC_VERSION_MICRO 100 #define LIBAVCODEC_VERSION_INT AV_VERSION_INT(LIBAVCODEC_VERSION_MAJOR, \

1 0

avformat/movenc: Support encryption of H.265 stream in AnnexB format
by Vadym Bezdushnyi 29 Jun '21

29 Jun '21

ffmpeg | branch: master | Vadym Bezdushnyi <vadim.bezdush(a)gmail.com> | Mon Mar 1 14:53:48 2021 +0200| [b74beba9a9a317caa7ac973cb76cc6ab0ade7667] | committer: Gyan Doshi avformat/movenc: Support encryption of H.265 stream in AnnexB format Steps to test: 1. Create h265 test files - mp4 and h265 AnnexB streams: ffmpeg -f lavfi -i testsrc=duration=10:size=640x480:rate=30 -c:v hevc input_h265.mp4 ffmpeg -f lavfi -i testsrc=duration=10:size=640x480:rate=30 -c:v hevc -bsf:v hevc_mp4toannexb input_h265.h265 2. Encrypt and decrypt files. Put appropriate input file name here: input_h265.mp4 or input_h265.h265 ffmpeg -i input_h265.h265 -vcodec copy -acodec copy -encryption_scheme cenc-aes-ctr \ -encryption_key 00000000000000000000000000000000 -encryption_kid 00000000000000000000000000000000 \ encrypted_h265.mp4 ffplay -i encrypted_h265.mp4 -decryption_key 00000000000000000000000000000000 Signed-off-by: Vadym Bezdushnyi <vadim.bezdush(a)gmail.com> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=b74beba9a9a317caa… --- libavformat/movenc.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/libavformat/movenc.c b/libavformat/movenc.c index 04f3e94158..8fdce359db 100644 --- a/libavformat/movenc.c +++ b/libavformat/movenc.c @@ -5657,7 +5657,15 @@ int ff_mov_write_packet(AVFormatContext *s, AVPacket *pkt) return ret; avio_write(pb, reformatted_data, size); } else { - size = ff_hevc_annexb2mp4(pb, pkt->data, pkt->size, 0, NULL); + if (trk->cenc.aes_ctr) { + size = ff_mov_cenc_avc_parse_nal_units(&trk->cenc, pb, pkt->data, size); + if (size < 0) { + ret = size; + goto err; + } + } else { + size = ff_hevc_annexb2mp4(pb, pkt->data, pkt->size, 0, NULL); + } } } else if (par->codec_id == AV_CODEC_ID_AV1) { if (trk->hint_track >= 0 && trk->hint_track < mov->nb_streams) { @@ -5699,6 +5707,9 @@ int ff_mov_write_packet(AVFormatContext *s, AVPacket *pkt) if (par->codec_id == AV_CODEC_ID_H264 && par->extradata_size > 4) { int nal_size_length = (par->extradata[4] & 0x3) + 1; ret = ff_mov_cenc_avc_write_nal_units(s, &trk->cenc, nal_size_length, pb, pkt->data, size); + } else if(par->codec_id == AV_CODEC_ID_HEVC && par->extradata_size > 21) { + int nal_size_length = (par->extradata[21] & 0x3) + 1; + ret = ff_mov_cenc_avc_write_nal_units(s, &trk->cenc, nal_size_length, pb, pkt->data, size); } else { ret = ff_mov_cenc_write_packet(&trk->cenc, pb, pkt->data, size); } @@ -6710,7 +6721,8 @@ static int mov_init(AVFormatContext *s) if (mov->encryption_scheme == MOV_ENC_CENC_AES_CTR) { ret = ff_mov_cenc_init(&track->cenc, mov->encryption_key, - track->par->codec_id == AV_CODEC_ID_H264, s->flags & AVFMT_FLAG_BITEXACT); + (track->par->codec_id == AV_CODEC_ID_H264 || track->par->codec_id == AV_CODEC_ID_HEVC), + s->flags & AVFMT_FLAG_BITEXACT); if (ret) return ret; }

1 0

avfilter/vf_guided: support single input
by Xuewei Meng 29 Jun '21

29 Jun '21

ffmpeg | branch: master | Xuewei Meng <xwmeng96(a)gmail.com> | Mon Jun 14 10:08:01 2021 +0800| [9ca88b3befef5608dd2a58d08f3aabcd0b475f95] | committer: Steven Liu avfilter/vf_guided: support single input Support single input for guided filter by adding guidance mode. If the guidance mode is off, single input is required. And edge-preserving smoothing is conducted. If the mode is on, two inputs are needed. The second input serves as the guidance. For this mode, more tasks are supported, such as detail enhancement, dehazing and so on. Signed-off-by: Xuewei Meng <xwmeng96(a)gmail.com> Reviewed-by: Steven Liu <lq(a)chinaffmpeg.org> > http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=9ca88b3befef5608d… --- doc/filters.texi | 12 ++-- libavfilter/vf_guided.c | 168 ++++++++++++++++++++++++++++++++---------------- 2 files changed, 119 insertions(+), 61 deletions(-) diff --git a/doc/filters.texi b/doc/filters.texi index bbd0a3d14d..67ad228d8b 100644 --- a/doc/filters.texi +++ b/doc/filters.texi @@ -12995,8 +12995,6 @@ greyedge=difford=1:minknorm=0:sigma=2 @section guided Apply guided filter for edge-preserving smoothing, dehazing and so on. -This filter requires two inputs of same resolution and pixel format. -The second input serves as the reference. The filter accepts the following options: @table @option @@ -13017,6 +13015,12 @@ Set subsampling ratio for @code{fast} mode. Range is 2 to 64. Default is 4. No subsampling occurs in @code{basic} mode. +@item guidance +Set guidance mode. Can be @code{off} or @code{on}. Default is @code{off}. +If @code{off}, single input is required. +If @code{on}, two inputs of the same resolution and pixel format are required. +The second input serves as the guidance. + @item planes Set planes to filter. Default is first only. @end table @@ -13029,7 +13033,7 @@ This filter supports the all above options as @ref{commands}. @item Edge-preserving smoothing with guided filter: @example -ffmpeg -i in.png -i in.png -filter_complex guided out.png +ffmpeg -i in.png -vf guided out.png @end example @item @@ -13037,7 +13041,7 @@ Dehazing, structure-transferring filtering, detail enhancement with guided filte For the generation of guidance image, refer to paper "Guided Image Filtering". See: @url{http://kaiminghe.com/publications/pami12guidedfilter.pdf}. @example -ffmpeg -i in.png -i guidance.png -filter_complex guided out.png +ffmpeg -i in.png -i guidance.png -filter_complex guided=guidance=on out.png @end example @end itemize diff --git a/libavfilter/vf_guided.c b/libavfilter/vf_guided.c index ea537e40c6..202a6a0586 100644 --- a/libavfilter/vf_guided.c +++ b/libavfilter/vf_guided.c @@ -22,6 +22,7 @@ #include "libavutil/opt.h" #include "libavutil/pixdesc.h" #include "avfilter.h" +#include "filters.h" #include "formats.h" #include "framesync.h" #include "internal.h" @@ -33,6 +34,12 @@ enum FilterModes { NB_MODES, }; +enum GuidanceModes { + OFF, + ON, + NB_GUIDANCE_MODES, +}; + typedef struct GuidedContext { const AVClass *class; FFFrameSync fs; @@ -41,7 +48,7 @@ typedef struct GuidedContext { float eps; int mode; int sub; - + int guidance; int planes; int width; @@ -59,13 +66,16 @@ typedef struct GuidedContext { #define FLAGS AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_FILTERING_PARAM|AV_OPT_FLAG_RUNTIME_PARAM static const AVOption guided_options[] = { - { "radius", "set the box radius", OFFSET(radius), AV_OPT_TYPE_INT, {.i64 = 3 }, 1, 20, FLAGS }, - { "eps", "set the regularization parameter (with square)", OFFSET(eps), AV_OPT_TYPE_FLOAT, {.dbl = 0.01 }, 0.0, 1, FLAGS }, - { "mode", "set filtering mode (0: basic mode; 1: fast mode)", OFFSET(mode), AV_OPT_TYPE_INT, {.i64 = BASIC}, BASIC, NB_MODES - 1, FLAGS, "mode" }, - { "basic", "basic guided filter", 0, AV_OPT_TYPE_CONST, {.i64 = BASIC}, 0, 0, FLAGS, "mode" }, - { "fast", "fast guided filter", 0, AV_OPT_TYPE_CONST, {.i64 = FAST }, 0, 0, FLAGS, "mode" }, - { "sub", "subsampling ratio for fast mode", OFFSET(sub), AV_OPT_TYPE_INT, {.i64 = 4 }, 2, 64, FLAGS }, - { "planes", "set planes to filter", OFFSET(planes), AV_OPT_TYPE_INT, {.i64=1 }, 0, 0xF, FLAGS }, + { "radius", "set the box radius", OFFSET(radius), AV_OPT_TYPE_INT, {.i64 = 3 }, 1, 20, FLAGS }, + { "eps", "set the regularization parameter (with square)", OFFSET(eps), AV_OPT_TYPE_FLOAT, {.dbl = 0.01 }, 0.0, 1, FLAGS }, + { "mode", "set filtering mode (0: basic mode; 1: fast mode)", OFFSET(mode), AV_OPT_TYPE_INT, {.i64 = BASIC}, BASIC, NB_MODES - 1, FLAGS, "mode" }, + { "basic", "basic guided filter", 0, AV_OPT_TYPE_CONST, {.i64 = BASIC}, 0, 0, FLAGS, "mode" }, + { "fast", "fast guided filter", 0, AV_OPT_TYPE_CONST, {.i64 = FAST }, 0, 0, FLAGS, "mode" }, + { "sub", "subsampling ratio for fast mode", OFFSET(sub), AV_OPT_TYPE_INT, {.i64 = 4 }, 2, 64, FLAGS }, + { "guidance", "set guidance mode (0: off mode; 1: on mode)", OFFSET(guidance), AV_OPT_TYPE_INT, {.i64 = OFF }, OFF, NB_GUIDANCE_MODES - 1, FLAGS, "guidance" }, + { "off", "only one input is enabled", 0, AV_OPT_TYPE_CONST, {.i64 = OFF }, 0, 0, FLAGS, "guidance" }, + { "on", "two inputs are required", 0, AV_OPT_TYPE_CONST, {.i64 = ON }, 0, 0, FLAGS, "guidance" }, + { "planes", "set planes to filter", OFFSET(planes), AV_OPT_TYPE_INT, {.i64 = 1 }, 0, 0xF, FLAGS }, { NULL } }; @@ -149,16 +159,6 @@ static int config_input(AVFilterLink *inlink) GuidedContext *s = ctx->priv; const AVPixFmtDescriptor *desc = av_pix_fmt_desc_get(inlink->format); - if (ctx->inputs[0]->w != ctx->inputs[1]->w || - ctx->inputs[0]->h != ctx->inputs[1]->h) { - av_log(ctx, AV_LOG_ERROR, "Width and height of input videos must be same.\n"); - return AVERROR(EINVAL); - } - if (ctx->inputs[0]->format != ctx->inputs[1]->format) { - av_log(ctx, AV_LOG_ERROR, "Inputs must be of same pixel format.\n"); - return AVERROR(EINVAL); - } - if (s->mode == BASIC) { s->sub = 1; } @@ -230,7 +230,7 @@ static int guided_##name(AVFilterContext *ctx, GuidedContext *s, meanB = av_calloc(w * h, sizeof(float)); \ \ if (!I || !II || !P || !IP || !meanI || !meanII || !meanP || \ - !meanIP || !A || !B || !meanA || !meanB){ \ + !meanIP || !A || !B || !meanA || !meanB) { \ ret = AVERROR(ENOMEM); \ goto end; \ } \ @@ -304,47 +304,54 @@ end: GUIDED(uint8_t, byte) GUIDED(uint16_t, word) -static int process_frame(FFFrameSync *fs) +static int filter_frame(AVFilterContext *ctx, AVFrame **out, AVFrame *in, AVFrame *ref) { - AVFilterContext *ctx = fs->parent; - GuidedContext *s = fs->opaque; + GuidedContext *s = ctx->priv; AVFilterLink *outlink = ctx->outputs[0]; - AVFrame *out_frame = NULL, *main_frame = NULL, *ref_frame = NULL; - int ret; - - ret = ff_framesync_dualinput_get(fs, &main_frame, &ref_frame); - if (ret < 0) - return ret; - - out_frame = ff_get_video_buffer(outlink, outlink->w, outlink->h); - if (!out_frame) { - av_frame_free(&main_frame); + *out = ff_get_video_buffer(outlink, outlink->w, outlink->h); + if (!*out) return AVERROR(ENOMEM); - } - av_frame_copy_props(out_frame, main_frame); + av_frame_copy_props(*out, in); for (int plane = 0; plane < s->nb_planes; plane++) { if (!(s->planes & (1 << plane))) { - av_image_copy_plane(out_frame->data[plane], out_frame->linesize[plane], - main_frame->data[plane], main_frame->linesize[plane], + av_image_copy_plane((*out)->data[plane], (*out)->linesize[plane], + in->data[plane], in->linesize[plane], s->planewidth[plane] * ((s->depth + 7) / 8), s->planeheight[plane]); continue; } if (s->depth <= 8) - guided_byte(ctx, s, main_frame->data[plane], ref_frame->data[plane], out_frame->data[plane], s->radius, s->eps, + guided_byte(ctx, s, in->data[plane], ref->data[plane], (*out)->data[plane], s->radius, s->eps, s->planewidth[plane], s->planeheight[plane], - main_frame->linesize[plane], ref_frame->linesize[plane], out_frame->linesize[plane], (1 << s->depth) - 1.f); + in->linesize[plane], ref->linesize[plane], (*out)->linesize[plane], (1 << s->depth) - 1.f); else - guided_word(ctx, s, main_frame->data[plane], ref_frame->data[plane], out_frame->data[plane], s->radius, s->eps, + guided_word(ctx, s, in->data[plane], ref->data[plane], (*out)->data[plane], s->radius, s->eps, s->planewidth[plane], s->planeheight[plane], - main_frame->linesize[plane] / 2, ref_frame->linesize[plane] / 2, out_frame->linesize[plane] / 2, (1 << s->depth) - 1.f); + in->linesize[plane] / 2, ref->linesize[plane] / 2, (*out)->linesize[plane] / 2, (1 << s->depth) - 1.f); + } + + return 0; +} + +static int process_frame(FFFrameSync *fs) +{ + AVFilterContext *ctx = fs->parent; + AVFilterLink *outlink = ctx->outputs[0]; + AVFrame *out_frame = NULL, *main_frame = NULL, *ref_frame = NULL; + int ret; + ret = ff_framesync_dualinput_get(fs, &main_frame, &ref_frame); + if (ret < 0) + return ret; + + ret = filter_frame(ctx, &out_frame, main_frame, ref_frame); + if (ret < 0) { + return ret; } av_frame_free(&main_frame); return ff_filter_frame(outlink, out_frame); } - static int config_output(AVFilterLink *outlink) { AVFilterContext *ctx = outlink->src; @@ -354,12 +361,27 @@ static int config_output(AVFilterLink *outlink) FFFrameSyncIn *in; int ret; + if (s->guidance == ON) { + if (ctx->inputs[0]->w != ctx->inputs[1]->w || + ctx->inputs[0]->h != ctx->inputs[1]->h) { + av_log(ctx, AV_LOG_ERROR, "Width and height of input videos must be same.\n"); + return AVERROR(EINVAL); + } + if (ctx->inputs[0]->format != ctx->inputs[1]->format) { + av_log(ctx, AV_LOG_ERROR, "Inputs must be of same pixel format.\n"); + return AVERROR(EINVAL); + } + } outlink->w = mainlink->w; outlink->h = mainlink->h; outlink->time_base = mainlink->time_base; outlink->sample_aspect_ratio = mainlink->sample_aspect_ratio; outlink->frame_rate = mainlink->frame_rate; + + if (s->guidance == OFF) + return 0; + if ((ret = ff_framesync_init(&s->fs, ctx, 2)) < 0) return ret; @@ -383,22 +405,66 @@ static int config_output(AVFilterLink *outlink) static int activate(AVFilterContext *ctx) { GuidedContext *s = ctx->priv; - return ff_framesync_activate(&s->fs); + AVFrame *frame = NULL; + AVFrame *out = NULL; + int ret, status; + int64_t pts; + if (s->guidance) + return ff_framesync_activate(&s->fs); + + FF_FILTER_FORWARD_STATUS_BACK(ctx->outputs[0], ctx->inputs[0]); + + if ((ret = ff_inlink_consume_frame(ctx->inputs[0], &frame)) > 0) { + ret = filter_frame(ctx, &out, frame, frame); + av_frame_free(&frame); + if (ret < 0) + return ret; + ret = ff_filter_frame(ctx->outputs[0], out); + } + if (ret < 0) + return ret; + if (ff_inlink_acknowledge_status(ctx->inputs[0], &status, &pts)) { + ff_outlink_set_status(ctx->outputs[0], status, pts); + return 0; + } + if (ff_outlink_frame_wanted(ctx->outputs[0])) + ff_inlink_request_frame(ctx->inputs[0]); + return 0; } static av_cold int init(AVFilterContext *ctx) { + GuidedContext *s = ctx->priv; + AVFilterPad pad = { 0 }; + int ret; + + pad.type = AVMEDIA_TYPE_VIDEO; + pad.name = "source"; + pad.config_props = config_input; + + if ((ret = ff_insert_inpad(ctx, 0, &pad)) < 0) + return ret; + + if (s->guidance == ON) { + pad.type = AVMEDIA_TYPE_VIDEO; + pad.name = "guidance"; + pad.config_props = NULL; + + if ((ret = ff_insert_inpad(ctx, 1, &pad)) < 0) + return ret; + } + return 0; } static av_cold void uninit(AVFilterContext *ctx) { GuidedContext *s = ctx->priv; - ff_framesync_uninit(&s->fs); + if (s->guidance == ON) + ff_framesync_uninit(&s->fs); return; } - static int process_command(AVFilterContext *ctx, const char *cmd, const char *arg, @@ -414,18 +480,6 @@ static int process_command(AVFilterContext *ctx, return 0; } -static const AVFilterPad guided_inputs[] = { - { - .name = "main", - .type = AVMEDIA_TYPE_VIDEO, - },{ - .name = "reference", - .type = AVMEDIA_TYPE_VIDEO, - .config_props = config_input, - }, - { NULL } -}; - static const AVFilterPad guided_outputs[] = { { .name = "default", @@ -444,7 +498,7 @@ const AVFilter ff_vf_guided = { .priv_size = sizeof(GuidedContext), .priv_class = &guided_class, .activate = activate, - .inputs = guided_inputs, + .inputs = NULL, .outputs = guided_outputs, .flags = AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC | AVFILTER_FLAG_SLICE_THREADS, .process_command = process_command,

1 0