X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=x264.h;h=097365a4be7b9074e04c1079d9efc22b5a8e60d5;hb=b7789b1f08e27103576d9b9f0feea9b75e2eca56;hp=839645bc0eb702b2066c8a1be225c0b669ac4c4b;hpb=95ed2720b7772199f04cc9a657632107bb1c548c;p=x264 diff --git a/x264.h b/x264.h index 839645bc..097365a4 100644 --- a/x264.h +++ b/x264.h @@ -35,14 +35,62 @@ #include -#define X264_BUILD 63 +#define X264_BUILD 102 /* x264_t: * opaque handler for encoder */ typedef struct x264_t x264_t; /**************************************************************************** - * Initialisation structure and function. + * NAL structure and functions + ****************************************************************************/ + +enum nal_unit_type_e +{ + NAL_UNKNOWN = 0, + NAL_SLICE = 1, + NAL_SLICE_DPA = 2, + NAL_SLICE_DPB = 3, + NAL_SLICE_DPC = 4, + NAL_SLICE_IDR = 5, /* ref_idc != 0 */ + NAL_SEI = 6, /* ref_idc == 0 */ + NAL_SPS = 7, + NAL_PPS = 8, + NAL_AUD = 9, + NAL_FILLER = 12, + /* ref_idc == 0 for 6,9,10,11,12 */ +}; +enum nal_priority_e +{ + NAL_PRIORITY_DISPOSABLE = 0, + NAL_PRIORITY_LOW = 1, + NAL_PRIORITY_HIGH = 2, + NAL_PRIORITY_HIGHEST = 3, +}; + +/* The data within the payload is already NAL-encapsulated; the ref_idc and type + * are merely in the struct for easy access by the calling application. + * All data returned in an x264_nal_t, including the data in p_payload, is no longer + * valid after the next call to x264_encoder_encode. Thus it must be used or copied + * before calling x264_encoder_encode or x264_encoder_headers again. */ +typedef struct +{ + int i_ref_idc; /* nal_priority_e */ + int i_type; /* nal_unit_type_e */ + int b_long_startcode; + int i_first_mb; /* If this NAL is a slice, the index of the first MB in the slice. */ + int i_last_mb; /* If this NAL is a slice, the index of the last MB in the slice. */ + + /* Size of payload in bytes. */ + int i_payload; + /* If param->b_annexb is set, Annex-B bytestream with startcode. + * Otherwise, startcode is replaced with a 4-byte size. + * This size is the size used in mp4/similar muxing; it is equal to i_payload-4 */ + uint8_t *p_payload; +} x264_nal_t; + +/**************************************************************************** + * Encoder parameters ****************************************************************************/ /* CPU flags */ @@ -57,9 +105,17 @@ typedef struct x264_t x264_t; #define X264_CPU_SSE2_IS_FAST 0x000100 /* a few functions are only faster on Core2 and Phenom */ #define X264_CPU_SSE3 0x000200 #define X264_CPU_SSSE3 0x000400 -#define X264_CPU_PHADD_IS_FAST 0x000800 /* pre-Penryn Core2 have a uselessly slow PHADD instruction */ -#define X264_CPU_SSE4 0x001000 /* SSE4.1 */ -#define X264_CPU_STACK_MOD4 0x002000 /* if stack is only mod4 and not mod16 */ +#define X264_CPU_SHUFFLE_IS_FAST 0x000800 /* Penryn, Nehalem, and Phenom have fast shuffle units */ +#define X264_CPU_STACK_MOD4 0x001000 /* if stack is only mod4 and not mod16 */ +#define X264_CPU_SSE4 0x002000 /* SSE4.1 */ +#define X264_CPU_SSE42 0x004000 /* SSE4.2 */ +#define X264_CPU_SSE_MISALIGN 0x008000 /* Phenom support for misaligned SSE instruction arguments */ +#define X264_CPU_LZCNT 0x010000 /* Phenom support for "leading zero count" instruction. */ +#define X264_CPU_ARMV6 0x020000 +#define X264_CPU_NEON 0x040000 /* ARM NEON */ +#define X264_CPU_FAST_NEON_MRC 0x080000 /* Transfer from NEON to ARM register is fast (Cortex-A9) */ +#define X264_CPU_SLOW_CTZ 0x100000 /* BSR/BSF x86 instructions are really slow on some CPUs */ +#define X264_CPU_SLOW_ATOM 0x200000 /* The Atom just sucks */ /* Analyse flags */ @@ -80,28 +136,41 @@ typedef struct x264_t x264_t; #define X264_CQM_FLAT 0 #define X264_CQM_JVT 1 #define X264_CQM_CUSTOM 2 -#define X264_RC_NONE -1 #define X264_RC_CQP 0 #define X264_RC_CRF 1 #define X264_RC_ABR 2 #define X264_AQ_NONE 0 #define X264_AQ_VARIANCE 1 +#define X264_AQ_AUTOVARIANCE 2 #define X264_B_ADAPT_NONE 0 #define X264_B_ADAPT_FAST 1 #define X264_B_ADAPT_TRELLIS 2 +#define X264_WEIGHTP_NONE 0 +#define X264_WEIGHTP_BLIND 1 +#define X264_WEIGHTP_SMART 2 +#define X264_B_PYRAMID_NONE 0 +#define X264_B_PYRAMID_STRICT 1 +#define X264_B_PYRAMID_NORMAL 2 +#define X264_KEYINT_MIN_AUTO 0 +#define X264_KEYINT_MAX_INFINITE (1<<30) +#define X264_OPEN_GOP_NONE 0 +#define X264_OPEN_GOP_NORMAL 1 +#define X264_OPEN_GOP_BLURAY 2 static const char * const x264_direct_pred_names[] = { "none", "spatial", "temporal", "auto", 0 }; static const char * const x264_motion_est_names[] = { "dia", "hex", "umh", "esa", "tesa", 0 }; +static const char * const x264_b_pyramid_names[] = { "none", "strict", "normal", 0 }; static const char * const x264_overscan_names[] = { "undef", "show", "crop", 0 }; static const char * const x264_vidformat_names[] = { "component", "pal", "ntsc", "secam", "mac", "undef", 0 }; static const char * const x264_fullrange_names[] = { "off", "on", 0 }; static const char * const x264_colorprim_names[] = { "", "bt709", "undef", "", "bt470m", "bt470bg", "smpte170m", "smpte240m", "film", 0 }; static const char * const x264_transfer_names[] = { "", "bt709", "undef", "", "bt470m", "bt470bg", "smpte170m", "smpte240m", "linear", "log100", "log316", 0 }; static const char * const x264_colmatrix_names[] = { "GBR", "bt709", "undef", "", "fcc", "bt470bg", "smpte170m", "smpte240m", "YCgCo", 0 }; +static const char * const x264_nal_hrd_names[] = { "none", "vbr", "cbr", 0 }; +static const char * const x264_open_gop_names[] = { "none", "normal", "bluray", 0 }; /* Colorspace type - * legacy only; nothing other than I420 is really supported. - */ + * legacy only; nothing other than I420 is really supported. */ #define X264_CSP_MASK 0x00ff /* */ #define X264_CSP_NONE 0x0000 /* Invalid mode */ #define X264_CSP_I420 0x0001 /* yuv 4:2:0 planar */ @@ -115,25 +184,33 @@ static const char * const x264_colmatrix_names[] = { "GBR", "bt709", "undef", "" #define X264_CSP_MAX 0x0009 /* end of list */ #define X264_CSP_VFLIP 0x1000 /* */ -/* Slice type - */ +/* Slice type */ #define X264_TYPE_AUTO 0x0000 /* Let x264 choose the right type */ #define X264_TYPE_IDR 0x0001 #define X264_TYPE_I 0x0002 #define X264_TYPE_P 0x0003 #define X264_TYPE_BREF 0x0004 /* Non-disposable B-frame */ #define X264_TYPE_B 0x0005 +#define X264_TYPE_KEYFRAME 0x0006 /* IDR or I depending on b_open_gop option */ #define IS_X264_TYPE_I(x) ((x)==X264_TYPE_I || (x)==X264_TYPE_IDR) #define IS_X264_TYPE_B(x) ((x)==X264_TYPE_B || (x)==X264_TYPE_BREF) -/* Log level - */ +/* Log level */ #define X264_LOG_NONE (-1) #define X264_LOG_ERROR 0 #define X264_LOG_WARNING 1 #define X264_LOG_INFO 2 #define X264_LOG_DEBUG 3 +/* Threading */ +#define X264_THREADS_AUTO 0 /* Automatically select optimal number of threads */ +#define X264_SYNC_LOOKAHEAD_AUTO (-1) /* Automatically select optimal lookahead thread buffer size */ + +/* HRD */ +#define X264_NAL_HRD_NONE 0 +#define X264_NAL_HRD_VBR 1 +#define X264_NAL_HRD_CBR 2 + /* Zones: override ratecontrol or other options for specific sections of the video. * See x264_encoder_reconfig() for which options can be changed. * If zones overlap, whichever comes later in the list takes precedence. */ @@ -151,7 +228,9 @@ typedef struct x264_param_t /* CPU flags */ unsigned int cpu; int i_threads; /* encode multiple frames in parallel */ + int b_sliced_threads; /* Whether to use slice-based threading. */ int b_deterministic; /* whether to allow non-deterministic optimizations when threaded */ + int i_sync_lookahead; /* threaded lookahead buffer */ /* Video Properties */ int i_width; @@ -160,6 +239,14 @@ typedef struct x264_param_t int i_level_idc; int i_frame_total; /* number of frames to encode if known, else 0 */ + /* NAL HRD + * Uses Buffering and Picture Timing SEIs to signal HRD + * The HRD in H.264 was not designed with VFR in mind. + * It is therefore not recommendeded to use NAL HRD with VFR. + * Furthermore, reconfiguring the VBV (via x264_encoder_reconfig) + * will currently generate invalid HRD. */ + int i_nal_hrd; + struct { /* they will be reduced to be 0 < x <= 65535 and prime */ @@ -177,19 +264,20 @@ typedef struct x264_param_t int i_chroma_loc; /* both top & bottom */ } vui; - int i_fps_num; - int i_fps_den; - /* Bitstream parameters */ int i_frame_reference; /* Maximum number of reference frames */ + int i_dpb_size; /* Force a DPB size larger than that implied by B-frames and reference frames. + * Useful in combination with interactive error resilience. */ int i_keyint_max; /* Force an IDR keyframe at this interval */ int i_keyint_min; /* Scenecuts closer together than this are coded as I, not IDR. */ int i_scenecut_threshold; /* how aggressively to insert extra I frames */ - int b_pre_scenecut; /* compute scenecut on lowres frames */ + int b_intra_refresh; /* Whether or not to use periodic intra refresh instead of IDR frames. */ + int i_bframe; /* how many b-frame between 2 references pictures */ int i_bframe_adaptive; int i_bframe_bias; - int b_bframe_pyramid; /* Keep some B-frames as references */ + int i_bframe_pyramid; /* Keep some B-frames as references: 0=off, 1=strict hierarchical, 2=normal */ + int i_open_gop; /* Open gop: 1=display order, 2=bluray compatibility braindamage mode */ int b_deblocking_filter; int i_deblocking_filter_alphac0; /* [-6, 6] -6 light filter, 6 strong */ @@ -199,6 +287,7 @@ typedef struct x264_param_t int i_cabac_init_idc; int b_interlaced; + int b_constrained_intra; int i_cqm_preset; char *psz_cqm_file; /* JM format */ @@ -223,9 +312,9 @@ typedef struct x264_param_t unsigned int inter; /* inter partitions */ int b_transform_8x8; + int i_weighted_pred; /* weighting for P-frames */ int b_weighted_bipred; /* implicit weighting for B-frames */ int i_direct_mv_pred; /* spatial vs temporal mv prediction */ - int i_direct_8x8_inference; /* forbid 4x4 direct partitions. -1 = auto, based on level */ int i_chroma_qp_offset; int i_me_method; /* motion estimation algorithm to use (X264_ME_*) */ @@ -233,14 +322,15 @@ typedef struct x264_param_t int i_mv_range; /* maximum length of a mv (in pixels). -1 = auto, based on level */ int i_mv_range_thread; /* minimum space between threads. -1 = auto, based on number of threads. */ int i_subpel_refine; /* subpixel motion estimation quality */ - int b_bidir_me; /* jointly optimize both MVs in B-frames */ int b_chroma_me; /* chroma ME for subpel and mode decision in P-frames */ - int b_bframe_rdo; /* RD based mode decision for B-frames */ - int b_mixed_references; /* allow each mb partition in P-frames to have it's own reference number */ + int b_mixed_references; /* allow each mb partition to have its own reference number */ int i_trellis; /* trellis RD quantization */ int b_fast_pskip; /* early SKIP detection on P-frames */ int b_dct_decimate; /* transform coefficient thresholding on P-frames */ int i_noise_reduction; /* adaptive pseudo-deadzone */ + float f_psy_rd; /* Psy RD strength */ + float f_psy_trellis; /* Psy trellis strength */ + int b_psy; /* Toggle all psy optimizations */ /* the deadzone size that will be used in luma quantization */ int i_luma_deadzone[2]; /* {inter, intra} */ @@ -261,6 +351,7 @@ typedef struct x264_param_t int i_bitrate; float f_rf_constant; /* 1pass VBR, nominal QP */ + float f_rf_constant_max; /* In CRF mode, maximum CRF as caused by VBV */ float f_rate_tolerance; int i_vbv_max_bitrate; int i_vbv_buffer_size; @@ -270,6 +361,8 @@ typedef struct x264_param_t int i_aq_mode; /* psy adaptive QP. (X264_AQ_*) */ float f_aq_strength; + int b_mb_tree; /* Macroblock-tree ratecontrol. */ + int i_lookahead; /* 2pass */ int b_stat_write; /* Enable stat writing in psz_stat_out */ @@ -289,9 +382,89 @@ typedef struct x264_param_t /* Muxing parameters */ int b_aud; /* generate access unit delimiters */ int b_repeat_headers; /* put SPS/PPS before each keyframe */ + int b_annexb; /* if set, place start codes (4 bytes) before NAL units, + * otherwise place size (4 bytes) before NAL units. */ int i_sps_id; /* SPS and PPS id number */ + int b_vfr_input; /* VFR input */ + uint32_t i_fps_num; + uint32_t i_fps_den; + uint32_t i_timebase_num; /* Timebase numerator */ + uint32_t i_timebase_den; /* Timebase denominator */ + int b_dts_compress; /* DTS compression: this algorithm eliminates negative DTS + * by compressing them to be less than the second PTS. + * Warning: this will change the timebase! */ + + int b_tff; + + /* Pulldown: + * The correct pic_struct must be passed with each input frame. + * The input timebase should be the timebase corresponding to the output framerate. This should be constant. + * e.g. for 3:2 pulldown timebase should be 1001/30000 + * The PTS passed with each frame must be the PTS of the frame after pulldown is applied. + * Frame doubling and tripling require b_vfr_input set to zero (see H.264 Table D-1) + * + * Pulldown changes are not clearly defined in H.264. Therefore, it is the calling app's responsibility to manage this. + */ + + int b_pic_struct; + + /* Fake Interlaced. + * + * Used only when b_interlaced=0. Setting this flag makes it possible to flag the stream as PAFF interlaced yet + * encode all frames progessively. It is useful for encoding 25p and 30p Blu-Ray streams. + */ + + int b_fake_interlaced; + + /* Slicing parameters */ + int i_slice_max_size; /* Max size per slice in bytes; includes estimated NAL overhead. */ + int i_slice_max_mbs; /* Max number of MBs per slice; overrides i_slice_count. */ + int i_slice_count; /* Number of slices per frame: forces rectangular slices. */ + + /* Optional callback for freeing this x264_param_t when it is done being used. + * Only used when the x264_param_t sits in memory for an indefinite period of time, + * i.e. when an x264_param_t is passed to x264_t in an x264_picture_t or in zones. + * Not used when x264_encoder_reconfig is called directly. */ + void (*param_free)( void* ); + + /* Optional low-level callback for low-latency encoding. Called for each output NAL unit + * immediately after the NAL unit is finished encoding. This allows the calling application + * to begin processing video data (e.g. by sending packets over a network) before the frame + * is done encoding. + * + * This callback MUST do the following in order to work correctly: + * 1) Have available an output buffer of at least size nal->i_payload*3/2 + 5 + 16. + * 2) Call x264_nal_encode( h, dst, nal ), where dst is the output buffer. + * After these steps, the content of nal is valid and can be used in the same way as if + * the NAL unit were output by x264_encoder_encode. + * + * This does not need to be synchronous with the encoding process: the data pointed to + * by nal (both before and after x264_nal_encode) will remain valid until the next + * x264_encoder_encode call. The callback must be re-entrant. + * + * This callback does not work with frame-based threads; threads must be disabled + * or sliced-threads enabled. This callback also does not work as one would expect + * with HRD -- since the buffering period SEI cannot be calculated until the frame + * is finished encoding, it will not be sent via this callback. + * + * Note also that the NALs are not necessarily returned in order when sliced threads is + * enabled. Accordingly, the variable i_first_mb and i_last_mb are available in + * x264_nal_t to help the calling application reorder the slices if necessary. + * + * When this callback is enabled, x264_encoder_encode does not return valid NALs; + * the calling application is expected to acquire all output NALs through the callback. + * + * It is generally sensible to combine this callback with a use of slice-max-mbs or + * slice-max-size. */ + void (*nalu_process) ( x264_t *h, x264_nal_t *nal ); } x264_param_t; +void x264_nal_encode( x264_t *h, uint8_t *dst, x264_nal_t *nal ); + +/**************************************************************************** + * H.264 level restriction information + ****************************************************************************/ + typedef struct { int level_idc; int mbps; /* max macroblock processing rate (macroblocks/sec) */ @@ -302,6 +475,7 @@ typedef struct { int mv_range; /* max vertical mv component range (pixels) */ int mvs_per_2mb; /* max mvs per 2 consecutive mbs. */ int slice_rate; /* ?? */ + int mincr; /* min compression ratio */ int bipred8x8; /* limit bipred to >=8x8 */ int direct8x8; /* limit b_direct to >=8x8 */ int frame_only; /* forbid interlacing */ @@ -310,6 +484,10 @@ typedef struct { /* all of the levels defined in the standard, terminated by .level_idc=0 */ extern const x264_level_t x264_levels[]; +/**************************************************************************** + * Basic parameter handling functions + ****************************************************************************/ + /* x264_param_default: * fill x264_param_t with default values and do CPU detection */ void x264_param_default( x264_param_t * ); @@ -326,34 +504,163 @@ void x264_param_default( x264_param_t * ); int x264_param_parse( x264_param_t *, const char *name, const char *value ); /**************************************************************************** - * Picture structures and functions. + * Advanced parameter handling functions ****************************************************************************/ + +/* These functions expose the full power of x264's preset-tune-profile system for + * easy adjustment of large numbers of internal parameters. + * + * In order to replicate x264CLI's option handling, these functions MUST be called + * in the following order: + * 1) x264_param_default_preset + * 2) Custom user options (via param_parse or directly assigned variables) + * 3) x264_param_apply_fastfirstpass + * 4) x264_param_apply_profile + * + * Additionally, x264CLI does not apply step 3 if the preset chosen is "placebo" + * or --slow-firstpass is set. */ + +/* x264_param_default_preset: + * The same as x264_param_default, but also use the passed preset and tune + * to modify the default settings. + * (either can be NULL, which implies no preset or no tune, respectively) + * + * Currently available presets are, ordered from fastest to slowest: */ +static const char * const x264_preset_names[] = { "ultrafast", "superfast", "veryfast", "faster", "fast", "medium", "slow", "slower", "veryslow", "placebo", 0 }; + +/* Warning: the speed of these presets scales dramatically. Ultrafast is a full + * 100 times faster than placebo! + * + * Currently available tunings are: */ +static const char * const x264_tune_names[] = { "film", "animation", "grain", "stillimage", "psnr", "ssim", "fastdecode", "zerolatency", 0 }; + +/* Multiple tunings can be used if separated by a delimiter in ",./-+", + * however multiple psy tunings cannot be used. + * film, animation, grain, stillimage, psnr, and ssim are psy tunings. + * + * returns 0 on success, negative on failure (e.g. invalid preset/tune name). */ +int x264_param_default_preset( x264_param_t *, const char *preset, const char *tune ); + +/* x264_param_apply_fastfirstpass: + * If first-pass mode is set (rc.b_stat_read == 0, rc.b_stat_write == 1), + * modify the encoder settings to disable options generally not useful on + * the first pass. */ +void x264_param_apply_fastfirstpass( x264_param_t * ); + +/* x264_param_apply_profile: + * Applies the restrictions of the given profile. + * Currently available profiles are, from most to least restrictive: */ +static const char * const x264_profile_names[] = { "baseline", "main", "high", 0 }; + +/* (can be NULL, in which case the function will do nothing) + * + * Does NOT guarantee that the given profile will be used: if the restrictions + * of "High" are applied to settings that are already Baseline-compatible, the + * stream will remain baseline. In short, it does not increase settings, only + * decrease them. + * + * returns 0 on success, negative on failure (e.g. invalid profile name). */ +int x264_param_apply_profile( x264_param_t *, const char *profile ); + +/**************************************************************************** + * Picture structures and functions + ****************************************************************************/ + +enum pic_struct_e +{ + PIC_STRUCT_AUTO = 0, // automatically decide (default) + PIC_STRUCT_PROGRESSIVE = 1, // progressive frame + // "TOP" and "BOTTOM" are not supported in x264 (PAFF only) + PIC_STRUCT_TOP_BOTTOM = 4, // top field followed by bottom + PIC_STRUCT_BOTTOM_TOP = 5, // bottom field followed by top + PIC_STRUCT_TOP_BOTTOM_TOP = 6, // top field, bottom field, top field repeated + PIC_STRUCT_BOTTOM_TOP_BOTTOM = 7, // bottom field, top field, bottom field repeated + PIC_STRUCT_DOUBLE = 8, // double frame + PIC_STRUCT_TRIPLE = 9, // triple frame +}; + typedef struct { - int i_csp; + double cpb_initial_arrival_time; + double cpb_final_arrival_time; + double cpb_removal_time; + + double dpb_output_time; +} x264_hrd_t; - int i_plane; - int i_stride[4]; - uint8_t *plane[4]; +typedef struct +{ + int i_csp; /* Colorspace */ + int i_plane; /* Number of image planes */ + int i_stride[4]; /* Strides for each plane */ + uint8_t *plane[4]; /* Pointers to each plane */ } x264_image_t; typedef struct { - /* In: force picture type (if not auto) XXX: ignored for now + /* In: an array of quantizer offsets to be applied to this image during encoding. + * These are added on top of the decisions made by x264. + * Offsets can be fractional; they are added before QPs are rounded to integer. + * Adaptive quantization must be enabled to use this feature. Behavior if quant + * offsets differ between encoding passes is undefined. + * + * Array contains one offset per macroblock, in raster scan order. In interlaced + * mode, top-field MBs and bottom-field MBs are interleaved at the row level. */ + float *quant_offsets; + /* In: optional callback to free quant_offsets when used. + * Useful if one wants to use a different quant_offset array for each frame. */ + void (*quant_offsets_free)( void* ); +} x264_image_properties_t; + +typedef struct +{ + /* In: force picture type (if not auto) + * If x264 encoding parameters are violated in the forcing of picture types, + * x264 will correct the input picture type and log a warning. + * The quality of frametype decisions may suffer if a great deal of fine-grained + * mixing of auto and forced frametypes is done. * Out: type of the picture encoded */ int i_type; /* In: force quantizer for > 0 */ int i_qpplus1; + /* In: pic_struct, for pulldown/doubling/etc...used only if b_pic_timing_sei=1. + * use pic_struct_e for pic_struct inputs */ + int i_pic_struct; + /* Out: whether this frame is a keyframe. Important when using modes that result in + * SEI recovery points being used instead of IDR frames. */ + int b_keyframe; /* In: user pts, Out: pts of encoded picture (user)*/ int64_t i_pts; - + /* Out: frame dts. Since the pts of the first frame is always zero, + * initial frames may have a negative dts which must be dealt with by any muxer */ + int64_t i_dts; + /* In: custom encoding parameters to be set from this frame forwards + (in coded order, not display order). If NULL, continue using + parameters from the previous frame. Some parameters, such as + aspect ratio, can only be changed per-GOP due to the limitations + of H.264 itself; in this case, the caller must force an IDR frame + if it needs the changed parameter to apply immediately. */ + x264_param_t *param; /* In: raw data */ x264_image_t img; + /* In: optional information to modify encoder decisions for this frame */ + x264_image_properties_t prop; + /* Out: HRD timing information. Output only when i_nal_hrd is set. */ + x264_hrd_t hrd_timing; + /* private user data. libx264 doesn't touch this, + not even copy it from input to output frames. */ + void *opaque; } x264_picture_t; +/* x264_picture_init: + * initialize an x264_picture_t. Needs to be done if the calling application + * allocates its own x264_picture_t as opposed to using x264_picture_alloc. */ +void x264_picture_init( x264_picture_t *pic ); + /* x264_picture_alloc: - * alloc data for a picture. You must call x264_picture_clean on it. */ -void x264_picture_alloc( x264_picture_t *pic, int i_csp, int i_width, int i_height ); + * alloc data for a picture. You must call x264_picture_clean on it. + * returns 0 on success, or -1 on malloc failure. */ +int x264_picture_alloc( x264_picture_t *pic, int i_csp, int i_width, int i_height ); /* x264_picture_clean: * free associated resource for a x264_picture_t allocated with @@ -361,70 +668,91 @@ void x264_picture_alloc( x264_picture_t *pic, int i_csp, int i_width, int i_heig void x264_picture_clean( x264_picture_t *pic ); /**************************************************************************** - * NAL structure and functions: + * Encoder functions ****************************************************************************/ -/* nal */ -enum nal_unit_type_e -{ - NAL_UNKNOWN = 0, - NAL_SLICE = 1, - NAL_SLICE_DPA = 2, - NAL_SLICE_DPB = 3, - NAL_SLICE_DPC = 4, - NAL_SLICE_IDR = 5, /* ref_idc != 0 */ - NAL_SEI = 6, /* ref_idc == 0 */ - NAL_SPS = 7, - NAL_PPS = 8, - NAL_AUD = 9, - /* ref_idc == 0 for 6,9,10,11,12 */ -}; -enum nal_priority_e -{ - NAL_PRIORITY_DISPOSABLE = 0, - NAL_PRIORITY_LOW = 1, - NAL_PRIORITY_HIGH = 2, - NAL_PRIORITY_HIGHEST = 3, -}; -typedef struct -{ - int i_ref_idc; /* nal_priority_e */ - int i_type; /* nal_unit_type_e */ - - /* This data are raw payload */ - int i_payload; - uint8_t *p_payload; -} x264_nal_t; - -/* x264_nal_encode: - * encode a nal into a buffer, setting the size. - * if b_annexeb then a long synch work is added - * XXX: it currently doesn't check for overflow */ -int x264_nal_encode( void *, int *, int b_annexeb, x264_nal_t *nal ); - -/* x264_nal_decode: - * decode a buffer nal into a x264_nal_t */ -int x264_nal_decode( x264_nal_t *nal, void *, int ); - -/**************************************************************************** - * Encoder functions: - ****************************************************************************/ +/* Force a link error in the case of linking against an incompatible API version. + * Glue #defines exist to force correct macro expansion; the final output of the macro + * is x264_encoder_open_##X264_BUILD (for purposes of dlopen). */ +#define x264_encoder_glue1(x,y) x##y +#define x264_encoder_glue2(x,y) x264_encoder_glue1(x,y) +#define x264_encoder_open x264_encoder_glue2(x264_encoder_open_,X264_BUILD) /* x264_encoder_open: * create a new encoder handler, all parameters from x264_param_t are copied */ -x264_t *x264_encoder_open ( x264_param_t * ); +x264_t *x264_encoder_open( x264_param_t * ); + /* x264_encoder_reconfig: - * change encoder options while encoding, - * analysis-related parameters from x264_param_t are copied */ + * various parameters from x264_param_t are copied. + * this takes effect immediately, on whichever frame is encoded next; + * due to delay, this may not be the next frame passed to encoder_encode. + * if the change should apply to some particular frame, use x264_picture_t->param instead. + * returns 0 on success, negative on parameter validation error. + * not all parameters can be changed; see the actual function for a detailed breakdown. */ int x264_encoder_reconfig( x264_t *, x264_param_t * ); +/* x264_encoder_parameters: + * copies the current internal set of parameters to the pointer provided + * by the caller. useful when the calling application needs to know + * how x264_encoder_open has changed the parameters, or the current state + * of the encoder after multiple x264_encoder_reconfig calls. + * note that the data accessible through pointers in the returned param struct + * (e.g. filenames) should not be modified by the calling application. */ +void x264_encoder_parameters( x264_t *, x264_param_t * ); /* x264_encoder_headers: - * return the SPS and PPS that will be used for the whole stream */ -int x264_encoder_headers( x264_t *, x264_nal_t **, int * ); + * return the SPS and PPS that will be used for the whole stream. + * *pi_nal is the number of NAL units outputted in pp_nal. + * returns negative on error. + * the payloads of all output NALs are guaranteed to be sequential in memory. */ +int x264_encoder_headers( x264_t *, x264_nal_t **pp_nal, int *pi_nal ); /* x264_encoder_encode: - * encode one picture */ -int x264_encoder_encode ( x264_t *, x264_nal_t **, int *, x264_picture_t *, x264_picture_t * ); + * encode one picture. + * *pi_nal is the number of NAL units outputted in pp_nal. + * returns negative on error, zero if no NAL units returned. + * the payloads of all output NALs are guaranteed to be sequential in memory. */ +int x264_encoder_encode( x264_t *, x264_nal_t **pp_nal, int *pi_nal, x264_picture_t *pic_in, x264_picture_t *pic_out ); /* x264_encoder_close: * close an encoder handler */ void x264_encoder_close ( x264_t * ); +/* x264_encoder_delayed_frames: + * return the number of currently delayed (buffered) frames + * this should be used at the end of the stream, to know when you have all the encoded frames. */ +int x264_encoder_delayed_frames( x264_t * ); +/* x264_encoder_intra_refresh: + * If an intra refresh is not in progress, begin one with the next P-frame. + * If an intra refresh is in progress, begin one as soon as the current one finishes. + * Requires that b_intra_refresh be set. + * + * Useful for interactive streaming where the client can tell the server that packet loss has + * occurred. In this case, keyint can be set to an extremely high value so that intra refreshes + * only occur when calling x264_encoder_intra_refresh. + * + * In multi-pass encoding, if x264_encoder_intra_refresh is called differently in each pass, + * behavior is undefined. + * + * Should not be called during an x264_encoder_encode. */ +void x264_encoder_intra_refresh( x264_t * ); +/* x264_encoder_invalidate_reference: + * An interactive error resilience tool, designed for use in a low-latency one-encoder-few-clients + * system. When the client has packet loss or otherwise incorrectly decodes a frame, the encoder + * can be told with this command to "forget" the frame and all frames that depend on it, referencing + * only frames that occurred before the loss. This will force a keyframe if no frames are left to + * reference after the aforementioned "forgetting". + * + * It is strongly recommended to use a large i_dpb_size in this case, which allows the encoder to + * keep around extra, older frames to fall back on in case more recent frames are all invalidated. + * Unlike increasing i_frame_reference, this does not increase the number of frames used for motion + * estimation and thus has no speed impact. It is also recommended to set a very large keyframe + * interval, so that keyframes are not used except as necessary for error recovery. + * + * x264_encoder_invalidate_reference is not currently compatible with the use of B-frames or intra + * refresh. + * + * In multi-pass encoding, if x264_encoder_invalidate_reference is called differently in each pass, + * behavior is undefined. + * + * Should not be called during an x264_encoder_encode. + * + * Returns 0 on success, negative on failure. */ +int x264_encoder_invalidate_reference( x264_t *, int64_t pts ); #endif