[FFmpeg-devel] [PATCH v3] avformat/mov: Add support for demuxing still HEIC images
Vittorio Giovara
vittorio.giovara at gmail.com
Thu Oct 5 20:36:11 EEST 2023
On Wed, Oct 4, 2023 at 12:40 PM Vignesh Venkatasubramanian via ffmpeg-devel
<ffmpeg-devel at ffmpeg.org> wrote:
> They are similar to AVIF images (both use the HEIF container).
> The only additional work needed is to parse the hvcC box and put
> it in the extradata.
>
> With this patch applied, ffmpeg (when built with an HEVC decoder)
> is able to decode the files in
> https://github.com/nokiatech/heif/tree/gh-pages/content/images
>
> Also add a couple of fate tests with samples from
> https://github.com/nokiatech/heif_conformance/tree/master/conformance_files
>
> Partially fixes trac ticket #6521.
>
> Signed-off-by: Vignesh Venkatasubramanian <vigneshv at google.com>
> ---
> libavformat/isom.h | 2 +
> libavformat/mov.c | 41 ++++++++++++++++++-
> tests/fate/mov.mak | 6 +++
> .../fate/mov-heic-demux-still-image-1-item | 11 +++++
> .../mov-heic-demux-still-image-multiple-items | 11 +++++
> 5 files changed, 70 insertions(+), 1 deletion(-)
> create mode 100644 tests/ref/fate/mov-heic-demux-still-image-1-item
> create mode 100644
> tests/ref/fate/mov-heic-demux-still-image-multiple-items
>
> diff --git a/libavformat/isom.h b/libavformat/isom.h
> index 3d375d7a46..b30b9da65e 100644
> --- a/libavformat/isom.h
> +++ b/libavformat/isom.h
> @@ -327,6 +327,8 @@ typedef struct MOVContext {
> int64_t extent_offset;
> } *avif_info;
> int avif_info_size;
> + int64_t hvcC_offset;
> + int hvcC_size;
> int interleaved_read;
> } MOVContext;
>
> diff --git a/libavformat/mov.c b/libavformat/mov.c
> index 294c864fbd..d3747022bd 100644
> --- a/libavformat/mov.c
> +++ b/libavformat/mov.c
> @@ -1218,7 +1218,8 @@ static int mov_read_ftyp(MOVContext *c, AVIOContext
> *pb, MOVAtom atom)
> c->isom = 1;
> av_log(c->fc, AV_LOG_DEBUG, "ISO: File Type Major Brand:
> %.4s\n",(char *)&type);
> av_dict_set(&c->fc->metadata, "major_brand", type, 0);
> - c->is_still_picture_avif = !strncmp(type, "avif", 4);
> + c->is_still_picture_avif = !strncmp(type, "avif", 4) ||
> + !strncmp(type, "mif1", 4);
> minor_ver = avio_rb32(pb); /* minor version */
> av_dict_set_int(&c->fc->metadata, "minor_version", minor_ver, 0);
>
> @@ -4911,6 +4912,19 @@ static int avif_add_stream(MOVContext *c, int
> item_id)
> st->priv_data = sc;
> st->codecpar->codec_type = AVMEDIA_TYPE_VIDEO;
> st->codecpar->codec_id = AV_CODEC_ID_AV1;
> + if (c->hvcC_offset >= 0) {
> + int ret;
> + int64_t pos = avio_tell(c->fc->pb);
> + st->codecpar->codec_id = AV_CODEC_ID_HEVC;
> + if (avio_seek(c->fc->pb, c->hvcC_offset, SEEK_SET) !=
> c->hvcC_offset) {
> + av_log(c->fc, AV_LOG_ERROR, "Failed to seek to hvcC data.\n");
> + return AVERROR_UNKNOWN;
> + }
> + ret = ff_get_extradata(c->fc, st->codecpar, c->fc->pb,
> c->hvcC_size);
> + if (ret < 0)
> + return ret;
> + avio_seek(c->fc->pb, pos, SEEK_SET);
> + }
> sc->ffindex = st->index;
> c->trak_index = st->index;
> st->avg_frame_rate.num = st->avg_frame_rate.den = 1;
> @@ -4953,6 +4967,8 @@ static int avif_add_stream(MOVContext *c, int
> item_id)
>
> static int mov_read_meta(MOVContext *c, AVIOContext *pb, MOVAtom atom)
> {
> + c->hvcC_offset = -1;
> + c->hvcC_size = 0;
> while (atom.size > 8) {
> uint32_t tag;
> if (avio_feof(pb))
> @@ -7827,6 +7843,28 @@ static int mov_read_iloc(MOVContext *c, AVIOContext
> *pb, MOVAtom atom)
> return atom.size;
> }
>
> +static int mov_read_iprp(MOVContext *c, AVIOContext *pb, MOVAtom atom)
> +{
> + int size = avio_rb32(pb);
> + if (avio_rl32(pb) != MKTAG('i','p','c','o'))
> + return AVERROR_INVALIDDATA;
> + size -= 8;
> + while (size > 0) {
> + int sub_size, sub_type;
> + sub_size = avio_rb32(pb);
> + sub_type = avio_rl32(pb);
> + sub_size -= 8;
> + size -= sub_size + 8;
> + if (sub_type == MKTAG('h','v','c','C')) {
> + c->hvcC_offset = avio_tell(pb);
> + c->hvcC_size = sub_size;
> + break;
> + }
> + avio_skip(pb, sub_size);
> + }
> + return atom.size;
> +}
> +
> static const MOVParseTableEntry mov_default_parse_table[] = {
> { MKTAG('A','C','L','R'), mov_read_aclr },
> { MKTAG('A','P','R','G'), mov_read_avid },
> @@ -7934,6 +7972,7 @@ static const MOVParseTableEntry
> mov_default_parse_table[] = {
> { MKTAG('p','c','m','C'), mov_read_pcmc }, /* PCM configuration box */
> { MKTAG('p','i','t','m'), mov_read_pitm },
> { MKTAG('e','v','c','C'), mov_read_glbl },
> +{ MKTAG('i','p','r','p'), mov_read_iprp },
> { 0, NULL }
> };
>
> diff --git a/tests/fate/mov.mak b/tests/fate/mov.mak
> index 6cb493ceab..a2d3cc8013 100644
> --- a/tests/fate/mov.mak
> +++ b/tests/fate/mov.mak
> @@ -18,6 +18,8 @@ FATE_MOV = fate-mov-3elist \
> fate-mov-neg-firstpts-discard-frames \
> fate-mov-stream-shorter-than-movie \
> fate-mov-pcm-remux \
> + fate-mov-heic-demux-still-image-1-item \
> + fate-mov-heic-demux-still-image-multiple-items \
> # FIXME: Uncomment these two lines once the test files are uploaded to
> the fate
> # server.
> # fate-mov-avif-demux-still-image-1-item \
> @@ -152,6 +154,10 @@ fate-mov-mp4-ttml-dfxp: CMD = transcode srt
> $(TARGET_SAMPLES)/sub/SubRip_capabil
> # parsed.
> #fate-mov-avif-demux-still-image-multiple-items: CMD = framemd5 -i
> $(TARGET_SAMPLES)/avif/still_image_exif.avif -c:v copy
>
> +fate-mov-heic-demux-still-image-1-item: CMD = framemd5 -i
> $(TARGET_SAMPLES)/heif-conformance/C002.heic -c:v copy
> +
> +fate-mov-heic-demux-still-image-multiple-items: CMD = framemd5 -i
> $(TARGET_SAMPLES)/heif-conformance/C003.heic -c:v copy
> +
> # Resulting remux should have:
> # 1. first audio stream with AV_DISPOSITION_HEARING_IMPAIRED
> # 2. second audio stream with AV_DISPOSITION_VISUAL_IMPAIRED |
> DESCRIPTIONS
> diff --git a/tests/ref/fate/mov-heic-demux-still-image-1-item
> b/tests/ref/fate/mov-heic-demux-still-image-1-item
> new file mode 100644
> index 0000000000..c850c1ff9c
> --- /dev/null
> +++ b/tests/ref/fate/mov-heic-demux-still-image-1-item
> @@ -0,0 +1,11 @@
> +#format: frame checksums
> +#version: 2
> +#hash: MD5
> +#extradata 0, 100,
> 5444bf01e03182c73ae957179d560f4d
> +#tb 0: 1/1
> +#media_type 0: video
> +#codec_id 0: hevc
> +#dimensions 0: 1280x720
> +#sar 0: 0/1
> +#stream#, dts, pts, duration, size, hash
> +0, 0, 0, 1, 111554,
> 03ceabfab39afd2e2e796b9362111f32
> diff --git a/tests/ref/fate/mov-heic-demux-still-image-multiple-items
> b/tests/ref/fate/mov-heic-demux-still-image-multiple-items
> new file mode 100644
> index 0000000000..c850c1ff9c
> --- /dev/null
> +++ b/tests/ref/fate/mov-heic-demux-still-image-multiple-items
> @@ -0,0 +1,11 @@
> +#format: frame checksums
> +#version: 2
> +#hash: MD5
> +#extradata 0, 100,
> 5444bf01e03182c73ae957179d560f4d
> +#tb 0: 1/1
> +#media_type 0: video
> +#codec_id 0: hevc
> +#dimensions 0: 1280x720
> +#sar 0: 0/1
> +#stream#, dts, pts, duration, size, hash
> +0, 0, 0, 1, 111554,
> 03ceabfab39afd2e2e796b9362111f32
> --
patch lgtm. I dont have access to fate, can you send the samples to
https://ffmpeg.org/fate.html#Uploading-new-samples-to-the-fate-suite?
As soon as they are up, I'll merge this.
Thanks
--
Vittorio
More information about the ffmpeg-devel
mailing list