X-Git-Url: https://git.sesse.net/?a=blobdiff_plain;f=x264.h;h=8f505b12cae22f94658cea00a7acaa3436663384;hb=f2ced3ff5f42784efe1b1d37738a645aad3fd52a;hp=f317e9859c67eabf406bbb62a33fa72bf49ffab1;hpb=3e411be2a3132db8672cd6b2a33c159cfed79fb8;p=x264 diff --git a/x264.h b/x264.h index f317e985..8f505b12 100644 --- a/x264.h +++ b/x264.h @@ -1,10 +1,11 @@ /***************************************************************************** - * x264.h: h264 encoder library + * x264.h: x264 public header ***************************************************************************** - * Copyright (C) 2003-2008 x264 Project + * Copyright (C) 2003-2011 x264 project * * Authors: Laurent Aimar * Loren Merritt + * Fiona Glaser * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -19,6 +20,9 @@ * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA. + * + * This program is also available under a commercial proprietary license. + * For more information, contact us at licensing@x264.com. *****************************************************************************/ #ifndef X264_X264_H @@ -35,12 +39,62 @@ #include -#define X264_BUILD 86 +#include "x264_config.h" + +#define X264_BUILD 113 /* x264_t: * opaque handler for encoder */ typedef struct x264_t x264_t; +/**************************************************************************** + * 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 ****************************************************************************/ @@ -66,6 +120,10 @@ typedef struct x264_t x264_t; #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 */ +#define X264_CPU_AVX 0x400000 /* AVX support: requires OS support even if YMM registers + * aren't used. */ /* Analyse flags */ @@ -89,6 +147,7 @@ typedef struct x264_t x264_t; #define X264_RC_CQP 0 #define X264_RC_CRF 1 #define X264_RC_ABR 2 +#define X264_QP_AUTO 0 #define X264_AQ_NONE 0 #define X264_AQ_VARIANCE 1 #define X264_AQ_AUTOVARIANCE 2 @@ -96,11 +155,16 @@ typedef struct x264_t x264_t; #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_SIMPLE 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 }; @@ -111,21 +175,18 @@ 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. */ +/* Colorspace type */ #define X264_CSP_MASK 0x00ff /* */ #define X264_CSP_NONE 0x0000 /* Invalid mode */ #define X264_CSP_I420 0x0001 /* yuv 4:2:0 planar */ -#define X264_CSP_I422 0x0002 /* yuv 4:2:2 planar */ -#define X264_CSP_I444 0x0003 /* yuv 4:4:4 planar */ -#define X264_CSP_YV12 0x0004 /* yuv 4:2:0 planar */ -#define X264_CSP_YUYV 0x0005 /* yuv 4:2:2 packed */ -#define X264_CSP_RGB 0x0006 /* rgb 24bits */ -#define X264_CSP_BGR 0x0007 /* bgr 24bits */ -#define X264_CSP_BGRA 0x0008 /* bgr 32bits */ -#define X264_CSP_MAX 0x0009 /* end of list */ -#define X264_CSP_VFLIP 0x1000 /* */ +#define X264_CSP_YV12 0x0002 /* yvu 4:2:0 planar */ +#define X264_CSP_NV12 0x0003 /* yuv 4:2:0, with one y plane and one packed u+v */ +#define X264_CSP_MAX 0x0004 /* end of list */ +#define X264_CSP_VFLIP 0x1000 /* the csp is vertically flipped */ +#define X264_CSP_HIGH_DEPTH 0x2000 /* the csp has a depth of 16 bits per pixel component */ /* Slice type */ #define X264_TYPE_AUTO 0x0000 /* Let x264 choose the right type */ @@ -134,6 +195,7 @@ static const char * const x264_colmatrix_names[] = { "GBR", "bt709", "undef", "" #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) @@ -148,6 +210,11 @@ static const char * const x264_colmatrix_names[] = { "GBR", "bt709", "undef", "" #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. */ @@ -176,6 +243,14 @@ 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 */ @@ -193,11 +268,10 @@ 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 */ @@ -207,6 +281,7 @@ typedef struct x264_param_t int i_bframe_adaptive; int i_bframe_bias; 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 */ @@ -252,7 +327,7 @@ typedef struct x264_param_t 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_chroma_me; /* chroma ME for subpel and mode decision in P-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 */ @@ -273,13 +348,14 @@ typedef struct x264_param_t { int i_rc_method; /* X264_RC_* */ - int i_qp_constant; /* 0-51 */ + int i_qp_constant; /* 0 to (51 + 6*(x264_bit_depth-8)). 0=lossless */ int i_qp_min; /* min allowed QP value */ int i_qp_max; /* max allowed QP value */ int i_qp_step; /* max QP step between frames */ 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; @@ -307,18 +383,53 @@ typedef struct x264_param_t char *psz_zones; /* alternate method of specifying zones */ } rc; + /* Cropping Rectangle parameters: added to those implicitly defined by + non-mod16 video resolutions. */ + struct { + unsigned int i_left; + unsigned int i_top; + unsigned int i_right; + unsigned int i_bottom; + } crop_rect; + + /* frame packing arrangement flag */ + int i_frame_packing; + /* 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 */ - int i_timebase_num; /* Timebase numerator */ - int 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_vfr_input; /* VFR input. If 1, use timebase and timestamps for ratecontrol purposes. + * If 0, use fps only. */ + int b_pulldown; /* use explicity set timebase for CFR */ + 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_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. */ @@ -330,8 +441,41 @@ typedef struct x264_param_t * 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 ****************************************************************************/ @@ -346,6 +490,7 @@ 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 */ @@ -396,23 +541,29 @@ int x264_param_parse( x264_param_t *, const char *name, const char *value ); * (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", "veryfast", "faster", "fast", "medium", "slow", "slower", "veryslow", "placebo", 0 }; +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 +/* The presets can also be indexed numerically, as in: + * x264_param_default_preset( ¶m, "3", ... ) + * with ultrafast mapping to "0" and placebo mapping to "9". This mapping may + * of course change if new presets are added in between, but will always be + * ordered from fastest to slowest. + * + * 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", "psnr", "ssim", "fastdecode", "zerolatency", 0 }; +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, psnr, and ssim are psy tunings. + * 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 == 1, rc.b_stat_write == 0), + * 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 * ); @@ -420,7 +571,7 @@ 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 }; +static const char * const x264_profile_names[] = { "baseline", "main", "high", "high10", 0 }; /* (can be NULL, in which case the function will do nothing) * @@ -435,6 +586,62 @@ int x264_param_apply_profile( x264_param_t *, const char *profile ); /**************************************************************************** * Picture structures and functions ****************************************************************************/ + +/* x264_bit_depth: + * Specifies the number of bits per pixel that x264 uses. This is also the + * bit depth that x264 encodes in. If this value is > 8, x264 will read + * two bytes of input data for each pixel sample, and expect the upper + * (16-x264_bit_depth) bits to be zero. + * Note: The flag X264_CSP_HIGH_DEPTH must be used to specify the + * colorspace depth as well. */ +extern const int x264_bit_depth; + +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 +{ + double cpb_initial_arrival_time; + double cpb_final_arrival_time; + double cpb_removal_time; + + double dpb_output_time; +} x264_hrd_t; + +/* Arbitrary user SEI: + * Payload size is in bytes and the payload pointer must be valid. + * Payload types and syntax can be found in Annex D of the H.264 Specification. + * SEI payload alignment bits as described in Annex D must be included at the + * end of the payload if needed. + * The payload should not be NAL-encapsulated. + * Payloads are written first in order of input, apart from in the case when HRD + * is enabled where payloads are written after the Buffering Period SEI. */ + +typedef struct +{ + int payload_size; + int payload_type; + uint8_t *payload; +} x264_sei_payload_t; + +typedef struct +{ + int num_payloads; + x264_sei_payload_t *payloads; + /* In: optional callback to free each payload AND x264_sei_payload_t when used. */ + void (*sei_free)( void* ); +} x264_sei_t; + typedef struct { int i_csp; /* Colorspace */ @@ -443,6 +650,22 @@ typedef struct uint8_t *plane[4]; /* Pointers to each plane */ } x264_image_t; +typedef struct +{ + /* 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) @@ -452,14 +675,17 @@ typedef struct * mixing of auto and forced frametypes is done. * Out: type of the picture encoded */ int i_type; - /* In: force quantizer for > 0 */ + /* In: force quantizer for != X264_QP_AUTO */ int i_qpplus1; + /* In: pic_struct, for pulldown/doubling/etc...used only if b_pic_struct=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, + /* Out: frame dts. When the pts of the first frame is close to 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 @@ -471,14 +697,25 @@ typedef struct 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; + /* In: arbitrary user SEI (e.g subtitles, AFDs) */ + x264_sei_t extra_sei; /* 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. - * returns 0 on success, or -1 on malloc failure. */ + * returns 0 on success, or -1 on malloc failure or invalid colorspace. */ int x264_picture_alloc( x264_picture_t *pic, int i_csp, int i_width, int i_height ); /* x264_picture_clean: @@ -486,50 +723,6 @@ int x264_picture_alloc( x264_picture_t *pic, int i_csp, int i_width, int i_heigh * x264_picture_alloc ONLY */ void x264_picture_clean( x264_picture_t *pic ); -/**************************************************************************** - * 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, - /* 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 */ - - /* Size of payload in bytes. */ - int i_payload; - /* If param->b_annexb is set, Annex-B bytestream with 4-byte 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 functions ****************************************************************************/ @@ -580,5 +773,46 @@ void x264_encoder_close ( x264_t * ); * 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_maximum_delayed_frames( x264_t *h ): + * return the maximum number of delayed (buffered) frames that can occur with the current + * parameters. */ +int x264_encoder_maximum_delayed_frames( x264_t *h ); +/* 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, but multiple calls can be made simultaneously. + * + * Returns 0 on success, negative on failure. */ +int x264_encoder_invalidate_reference( x264_t *, int64_t pts ); #endif