Merge branch 'main' of ssh://forge.3gpp.org:29419/ivas-codec-pc/ivas-codec... (e5f2c259) · Commits · IVAS Codec Public Collaboration / IVAS Codec

apps/isar_post_rend.c

+11 −0

Original line number	Diff line number	Diff line
		@@ -681,6 +681,9 @@ int main(
		int argc,
		char **argv )
		{
		#ifdef FIX_1335_EXTREND_RETCODE
		bool mainFailed = true; /* Assume main failed until cleanup is reached without errors */
		#endif
		ISAR_POST_REND_HANDLE hIsarPostRend = NULL;
		RotFileReader *headRotReader = NULL;
		RotFileReader *externalOrientationFileReader = NULL;
		@@ -1222,6 +1225,10 @@ int main(
		* Close files and deallocate resources
		------------------------------------------------------------------------------------------/

		#ifdef FIX_1335_EXTREND_RETCODE
		mainFailed = false; /* This will stay set to true if cleanup is reached via a goto due to an error */

		#endif
		cleanup:

		free( inpInt16Buffer );
		@@ -1252,7 +1259,11 @@ cleanup:
		print_mem( NULL );
		#endif

		#ifdef FIX_1335_EXTREND_RETCODE
		return mainFailed ? -1 : 0;
		#else
		return 0;
		#endif
		}

apps/renderer.c

+40 −27

Original line number	Diff line number	Diff line
		@@ -232,13 +232,13 @@ static const CmdLnParser_Option cliOptions[] = {
		.id = CmdLnOptionId_inputFormat,
		.match = "input_format",
		.matchShort = "if",
		.description = "Audio format of input file (e.g. 5_1 or HOA3 or META, use -l for a list)",
		.description = "Audio format of input file (e.g. 5_1 or HOA3 or META,\nuse -l for a list)",
		},
		{
		.id = CmdLnOptionId_inputMetadata,
		.match = "input_metadata",
		.matchShort = "im",
		.description = "Space-separated list of path to metadata files for ISM or MASA inputs or BINAURAL_SPLIT_PCM input mode. For OMASA, ISM files must be specified first.",
		.description = "Space-separated list of path to metadata files for ISM/MASA/OMASA/\nOSBA/BINAURAL_SPLIT_PCM inputs. \nFor OMASA, ISM files must be specified first.",
		},
		{
		.id = CmdLnOptionId_outputFile,
		@@ -256,13 +256,13 @@ static const CmdLnParser_Option cliOptions[] = {
		.id = CmdLnOptionId_sampleRate,
		.match = "sample_rate",
		.matchShort = "fs",
		.description = "Input sampling rate in kHz (16, 32, 48) - required only with raw PCM inputs",
		.description = "Input sampling rate in kHz (16, 32, 48) - required only with raw\nPCM inputs",
		},
		{
		.id = CmdLnOptionId_trajFile,
		.match = "trajectory_file",
		.matchShort = "T",
		.description = "Head rotation trajectory file for simulation of head tracking (only for binaural outputs)",
		.description = "Head rotation trajectory file for simulation of head tracking\n(only for binaural outputs)",
		},
		{
		.id = CmdLnOptionId_outputMetadata,
		@@ -280,43 +280,43 @@ static const CmdLnParser_Option cliOptions[] = {
		.id = CmdLnOptionId_refRotFile,
		.match = "reference_rotation_file",
		.matchShort = "rf",
		.description = "Reference rotation trajectory file for simulation of head tracking (only for binaural outputs)",
		.description = "Reference rotation trajectory file for simulation of head tracking\n(only for binaural outputs)",
		},
		{
		.id = CmdLnOptionId_customHrtfFile,
		.match = "custom_hrtf",
		.matchShort = "hrtf",
		.description = "Custom HRTF file for binaural rendering (only for binaural outputs)",
		.description = "Custom HRTF file for binaural rendering\n(only for binaural outputs)",
		},
		{
		.id = CmdLnOptionId_renderConfigFile,
		.match = "render_config_parameters",
		.matchShort = "render_config",
		.description = "Binaural renderer configuration parameters in file (only for binaural outputs)",
		.description = "Binaural renderer configuration parameters in file\n(only for binaural outputs)",
		},
		{
		.id = CmdLnOptionId_nonDiegeticPan,
		.match = "non_diegetic_panning",
		.matchShort = "non_diegetic_pan",
		.description = "Panning mono non diegetic sound to stereo -90<= pan <= 90\nleft or l or 90->left, right or r or -90->right, center or c or 0 ->middle\n",
		.description = "Panning mono non diegetic sound to stereo -90<= pan <= 90\nleft or l or 90->left, right or r or -90->right,\ncenter or c or 0 ->middle",
		},
		{
		.id = CmdLnOptionId_orientationTracking,
		.match = "tracking_type",
		.matchShort = "otr",
		.description = "Head orientation tracking type: 'none', 'ref', 'avg' or `ref_vec` or `ref_vec_lev` (only for binaural outputs)",
		.description = "Head orientation tracking type: 'none', 'ref', 'avg' or `ref_vec`\nor `ref_vec_lev` (only for binaural outputs)",
		},
		{
		.id = CmdlnOptionId_lfePosition,
		.match = "lfe_position",
		.matchShort = "lp",
		.description = "Output LFE position. Comma-delimited triplet of [gain, azimuth, elevation] where gain is linear (like --gain, -g) and azimuth, elevation are in degrees.\nIf specified, overrides the default behavior which attempts to map input to output LFE channel(s)",
		.description = "Output LFE position. Comma-delimited triplet of [gain, azimuth,\nelevation] where gain is linear (like --gain, -g) and azimuth,\nelevation are in degrees. If specified, overrides the default\nbehavior which attempts to map input to output LFE channel(s)",
		},
		{
		.id = CmdlnOptionId_lfeMatrix,
		.match = "lfe_matrix",
		.matchShort = "lm",
		.description = "LFE panning matrix. File (CSV table) containing a matrix of dimensions [ num_input_lfe x num_output_channels ] with elements specifying linear routing gain (like --gain, -g). \nIf specified, overrides the output LFE position option and the default behavior which attempts to map input to output LFE channel(s)",
		.description = "LFE panning matrix. File (CSV table) containing a matrix of\ndimensions [ num_input_lfe x num_output_channels ] with elements\nspecifying linear routing gain (like --gain, -g). If specified,\noverrides the output LFE position option and the default\nbehavior which attempts to map input to output LFE channel(s)",
		},
		{
		.id = CmdLnOptionId_noDelayCmp,
		@@ -328,7 +328,7 @@ static const CmdLnParser_Option cliOptions[] = {
		.id = CmdLnOptionId_complexityLevel,
		.match = "complexity_level",
		.matchShort = "level",
		.description = "Complexity level, level = (1, 2, 3), will be defined after characterisation.",
		.description = "Complexity level, level = (1, 2, 3), will be defined after\ncharacterisation.",
		},
		{
		.id = CmdLnOptionId_quietModeEnabled,
		@@ -352,13 +352,13 @@ static const CmdLnParser_Option cliOptions[] = {
		.id = CmdLnOptionId_referenceVectorFile,
		.match = "reference_vector_file",
		.matchShort = "rvf",
		.description = "Reference vector trajectory file for simulation of head tracking (only for binaural outputs)",
		.description = "Reference vector trajectory file for simulation of head tracking\n(only for binaural outputs)",
		},
		{
		.id = CmdLnOptionId_exteriorOrientationFile,
		.match = "exterior_orientation_file",
		.matchShort = "exof",
		.description = "External orientation trajectory file for simulation of external orientations",
		.description = "External orientation trajectory file for simulation of external\norientations",
		},
		{
		.id = CmdLnOptionId_framing,
		@@ -370,19 +370,19 @@ static const CmdLnParser_Option cliOptions[] = {
		.id = CmdLnOptionId_syncMdDelay,
		.match = "sync_md_delay",
		.matchShort = "smd",
		.description = "Metadata Synchronization Delay in ms, Default is 0. Quantized by 5ms subframes for TDRenderer (13ms -> 10ms -> 2subframes)",
		.description = "Metadata Synchronization Delay in ms, Default is 0. Quantized by\n5ms subframes for TDRenderer (13ms -> 10ms -> 2subframes)",
		},
		{
		.id = CmdLnOptionId_directivityPatternId,
		.match = "ism_directivity_pattern_id",
		.matchShort = "dpid",
		.description = "Directivity pattern ID(s) = [ID1, ID2, ID3, ID4]. Space-separated list of up to 4 numbers (unsigned integers) can be specified for BINAURAL and BINAURAL_ROOM_REVERB output configuration.\nID1, ID2, ID3, ID4 specify the directivity pattern IDs used for ISMs 1,2,3 and 4 respectively.\nThis options needs to be accompanied by a render_config file, otherwise a default directivity pattern is used.",
		.description = "Directivity pattern ID(s) = [ID1, ID2, ID3, ID4]. Space-separated\nlist of up to 4 numbers (unsigned integers) can be specified for\nBINAURAL and BINAURAL_ROOM_REVERB output.\nID1, ID2, ID3, ID4 specify the directivity pattern IDs used for\nISMs 1,2,3 and 4 respectively. \nThis option needs to be accompanied by a render_config file,\notherwise a default directivity pattern is used.",
		},
		{
		.id = CmdLnOptionId_acousticEnvironmentId,
		.match = "acoustic_environment_id",
		.matchShort = "aeid",
		.description = "Acoustic environment ID (number > 0) alternatively, it can be a text file where each line contains \"ID duration\" for BINAURAL_ROOM_REVERB output configuration.",
		.description = "Acoustic environment ID (number > 0) alternatively, it can be\na text file where each line contains \"ID duration\" for\nBINAURAL_ROOM_REVERB output.",
		},
		};

		@@ -659,12 +659,15 @@ int main(
		int argc,
		char **argv )
		{
		#ifdef FIX_1335_EXTREND_RETCODE
		bool mainFailed = true; /* Assume main failed until cleanup is reached without errors */
		#endif
		IVAS_REND_HANDLE hIvasRend = NULL;
		RotFileReader *headRotReader = NULL;
		RotFileReader *externalOrientationFileReader = NULL;
		RotFileReader *referenceRotReader = NULL;
		IVAS_CLDFB_FILTER_BANK_HANDLE cldfbAna[IVAS_MAX_INPUT_CHANNELS];
		IVAS_CLDFB_FILTER_BANK_HANDLE cldfbSyn[IVAS_MAX_INPUT_CHANNELS];
		IVAS_CLDFB_FILTER_BANK_HANDLE cldfbAna[RENDERER_MAX_INPUT_CHANNELS];
		IVAS_CLDFB_FILTER_BANK_HANDLE cldfbSyn[RENDERER_MAX_INPUT_CHANNELS];
		int16_t cldfb_in_flag, CLDFBframeSize_smpls;
		SplitRendBFIFileReader *splitRendBFIReader = NULL;
		Vector3PairFileReader *referenceVectorReader = NULL;
		@@ -1965,6 +1968,10 @@ int main(
		* Close files and deallocate resources
		------------------------------------------------------------------------------------------/

		#ifdef FIX_1335_EXTREND_RETCODE
		mainFailed = false; /* This will stay set to true if cleanup is reached via a goto due to an error */

		#endif
		cleanup:

		free( inpInt16Buffer );
		@@ -2021,7 +2028,11 @@ cleanup:
		print_mem( NULL );
		#endif

		#ifdef FIX_1335_EXTREND_RETCODE
		return mainFailed ? -1 : 0;
		#else
		return 0;
		#endif
		}


		@@ -3722,6 +3733,7 @@ static void printSupportedAudioConfigs( void )
		"BINAURAL_SPLIT_CODED",
		"BINAURAL_ROOM_IR (output only)",
		"BINAURAL_ROOM_REVERB (output only)",
		"META (Scene description, input only)",
		};

		fprintf( stdout, "Supported audio formats:\n" );
		@@ -3729,6 +3741,7 @@ static void printSupportedAudioConfigs( void )
		{
		fprintf( stdout, "%s\n", supportedFormats[i] );
		}
		fprintf( stdout, "\n" );

		return;
		}
		@@ -3739,7 +3752,7 @@ static ivas_error parseLfePanMtxFile(
		{
		int16_t i, lfe_in, ch_out;
		const char *tok;
		char line[200]; /* > (10 chars * IVAS_MAX_OUTPUT_CHANNELS) i.e. "-999, " */
		char line[200]; /* > (10 chars * RENDERER_MAX_OUTPUT_CHANNELS) i.e. "-999, " */
		FILE *mtxFile;

		if ( strlen( lfeRoutingMatrixFilePath ) < 1 )
		@@ -3758,7 +3771,7 @@ static ivas_error parseLfePanMtxFile(
		any subsequent issue in file reading will gracefully exit the function */
		for ( lfe_in = 0; lfe_in < RENDERER_MAX_INPUT_LFE_CHANNELS; lfe_in++ )
		{
		for ( i = 0; i < IVAS_MAX_OUTPUT_CHANNELS; i++ )
		for ( i = 0; i < RENDERER_MAX_OUTPUT_CHANNELS; i++ )
		{
		( *lfePanMtx )[lfe_in][i] = 0.0f;
		}
		@@ -3786,7 +3799,7 @@ static ivas_error parseLfePanMtxFile(
		{
		continue;
		}
		if ( ch_out > IVAS_MAX_OUTPUT_CHANNELS )
		if ( ch_out > RENDERER_MAX_OUTPUT_CHANNELS )
		{
		break;
		}
		@@ -3827,13 +3840,13 @@ static void convertInputBuffer(
		if ( cldfb_in_flag )
		{
		int16_t slotIdx, numCldfbBands, numFloatPcmSamples;
		float fIn[IVAS_MAX_OUTPUT_CHANNELS][IVAS_MAX_FRAME_SIZE];
		float fIn[RENDERER_MAX_OUTPUT_CHANNELS][IVAS_MAX_FRAME_SIZE];

		numFloatPcmSamples = numFloatSamplesPerChannel >> 1;
		numCldfbBands = numFloatPcmSamples / IVAS_CLDFB_NO_COL_MAX;

		/* CLDFB Analysis*/
		assert( numIntSamplesPerChannel <= IVAS_MAX_OUTPUT_CHANNELS * IVAS_MAX_FRAME_SIZE );
		assert( numIntSamplesPerChannel <= RENDERER_MAX_OUTPUT_CHANNELS * IVAS_MAX_FRAME_SIZE );
		for ( smpl = 0; smpl < numFloatPcmSamples; ++smpl )
		{
		for ( chnl = 0; chnl < numChannels; ++chnl )
		@@ -3908,9 +3921,9 @@ static void convertOutputBuffer(
		if ( cldfb_in_flag )
		{
		int16_t slotIdx, numCldfbBands, numPcmSamples, b;
		float fIn[IVAS_MAX_OUTPUT_CHANNELS][IVAS_MAX_FRAME_SIZE];
		float re[IVAS_MAX_OUTPUT_CHANNELS][IVAS_CLDFB_NO_COL_MAX][IVAS_CLDFB_NO_CHANNELS_MAX];
		float im[IVAS_MAX_OUTPUT_CHANNELS][IVAS_CLDFB_NO_COL_MAX][IVAS_CLDFB_NO_CHANNELS_MAX];
		float fIn[RENDERER_MAX_OUTPUT_CHANNELS][IVAS_MAX_FRAME_SIZE];
		float re[RENDERER_MAX_OUTPUT_CHANNELS][IVAS_CLDFB_NO_COL_MAX][IVAS_CLDFB_NO_CHANNELS_MAX];
		float im[RENDERER_MAX_OUTPUT_CHANNELS][IVAS_CLDFB_NO_COL_MAX][IVAS_CLDFB_NO_CHANNELS_MAX];

		numPcmSamples = numSamplesPerChannel >> 1;
		numCldfbBands = numPcmSamples / IVAS_CLDFB_NO_COL_MAX;

lib_com/bitstream.c

+1984 −24

File changed.

Preview size limit exceeded, changes collapsed.

lib_com/common_api_types.h

+4 −5

Original line number	Diff line number	Diff line
		@@ -50,8 +50,7 @@
		#define IVAS_MAX_BITS_PER_FRAME ( 512000 / IVAS_NUM_FRAMES_PER_SEC ) /* maximum bits per frame; corresponds to maximum bitrate of 512 kbps */

		#define IVAS_MAX_NUM_OBJECTS 4
		#define IVAS_MAX_INPUT_CHANNELS 16
		#define IVAS_MAX_OUTPUT_CHANNELS 16 /* Note: there is an exception for OSBA and EXT otuput where it can be 20 (HOA3 + 4 ISM channels) */
		#define IVAS_MAX_LS_CHANNELS 16
		#define IVAS_CLDFB_NO_COL_MAX 16
		#define IVAS_CLDFB_NO_CHANNELS_MAX 60

		@@ -190,10 +189,10 @@ typedef struct ivas_LS_setup_custom IVAS_LSSETUP_CUSTOM_STRUCT;
		typedef struct _IVAS_LS_CUSTOM_LAYOUT
		{
		int16_t num_spk;
		float azimuth[IVAS_MAX_OUTPUT_CHANNELS];
		float elevation[IVAS_MAX_OUTPUT_CHANNELS];
		float azimuth[IVAS_MAX_LS_CHANNELS];
		float elevation[IVAS_MAX_LS_CHANNELS];
		int16_t num_lfe;
		int16_t lfe_idx[IVAS_MAX_OUTPUT_CHANNELS];
		int16_t lfe_idx[IVAS_MAX_LS_CHANNELS];

		} IVAS_CUSTOM_LS_DATA;

lib_com/ivas_cnst.h

+5 −5

Original line number	Diff line number	Diff line
		@@ -128,12 +128,12 @@ typedef enum
		* IVAS general constants
		----------------------------------------------------------------------------------/

		#define MAX_INPUT_CHANNELS 16 /* Maximum number of input channels (HOA 3rd order), == IVAS_MAX_INPUT_CHANNELS */
		#define MAX_INPUT_CHANNELS 16 /* Maximum number of input channels (HOA 3rd order or IVAS_MAX_LS_CHANNELS) without separate objects in combined formats */
		#define MAX_TRANSPORT_CHANNELS 12 /* Maximum number of transport channels */
		#define MAX_INTERN_CHANNELS 16 /* Maximum number of intern channels (HOA 3rd order) */
		#define HEAD_ROTATION_HOA_ORDER 3 /* HOA 3rd order */
		#define MAX_CICP_CHANNELS 16 /* max channels for loudspeaker layouts (16 for custom layouts)*/
		#define MAX_OUTPUT_CHANNELS 16 /* Maximum number of output channels (HOA 3rd order) without separate objects in combined formats */
		#define MAX_LS_CHANNELS 16 /* max channels for loudspeaker layouts (16 for custom layouts), == IVAS_MAX_LS_CHANNELS */
		#define MAX_OUTPUT_CHANNELS 16 /* Maximum number of output channels (HOA 3rd order or IVAS_MAX_LS_CHANNELS) without separate objects in combined formats */
		#define MAX_OUTPUT_CHANNELS_IN_DIEGETIC_PAN 2 /* Maximum number of output channels with non diegetic panning */

		#define BINAURAL_CHANNELS 2 /* number of channels for binaural output configuration */
		@@ -1505,7 +1505,7 @@ typedef enum
		* TD Binaural Object renderer
		----------------------------------------------------------------------------------/

		#define MAX_NUM_TDREND_CHANNELS MAX_CICP_CHANNELS /* max. number of channels in TD renderer (objects or loudspeaker channels) */
		#define MAX_NUM_TDREND_CHANNELS MAX_LS_CHANNELS /* max. number of channels in TD renderer (objects or loudspeaker channels) */

		#define SFX_SPAT_BIN_MAX_NO_OF_OUTPUT_SAMPLES 288 /* 288 = 6 msec @ 48 kHz. */
		#define HRTF_MODEL_N_SECTIONS 3 /* No. sections used in approximate evaluation of model */
		@@ -1608,7 +1608,7 @@ typedef enum

		#define IVAS_MAX_FB_MIXER_OUT_CH IVAS_SPAR_MAX_CH
		#define IVAS_MAX_SPAR_FB_MIXER_IN_CH IVAS_SPAR_MAX_CH
		#define IVAS_MAX_FB_MIXER_IN_CH MAX_CICP_CHANNELS
		#define IVAS_MAX_FB_MIXER_IN_CH MAX_LS_CHANNELS

		#define MAX_NUM_BANDS_DIFF_NON48K 3