x264源码解析：码率控制之VBV 帧级

• 码率控制之VBV
  x264源码解析：码率控制之VBV 帧级
  x264源码解析：码率控制之VBV 宏块级

---

VBV（Video Buffering Verifier）视频缓存检验器

背景

The Video Buffering Verifier is a theoretical MPEG video buffer model, used to ensure that an encoded video stream can be correctly buffered, and played back at the decoder device.

By definition, the VBV shall not overflow nor underflow when its input is a compliant stream, (except in the case of low_delay). It is therefore important when encoding such a stream that it comply with the VBV requirements.

使用场景

You should only use VBV if you have a hardware decoder that requires
it. It is highly recommended, though not required, to use 2pass
bitrate mode with VBV.

struct x264_ratecontrol_t
{
    int b_vbv;                  ///< VBV: mb row 
    int b_vbv_min_rate;         ///< is CBR
    /* VBV stuff */
    double buffer_size;
    int64_t buffer_fill_final;  ///< real bits for last frame
    int64_t buffer_fill_final_min;
    double buffer_fill;         /* planned buffer, if all in-progress frames hit their bit budget */
    double buffer_rate;         /* # of bits added to buffer_fill after each frame */
    double vbv_max_rate;        /* # of bits added to buffer_fill per second */
    predictor_t *pred;          /* predict frame size from satd */
    int single_frame_vbv;
    float rate_factor_max_increment; /* Don't allow RF above (CRF + this value). */
};

// apply VBV constraints and clip qscale to between lmin and lmax
static double clip_qscale( x264_t *h, int pict_type, double q )
{
    x264_ratecontrol_t *rcc = h->rc;
    double lmin = rcc->lmin[pict_type];
    double lmax = rcc->lmax[pict_type];
    if( rcc->rate_factor_max_increment )
        lmax = X264_MIN( lmax, qp2qscale( rcc->qp_novbv + rcc->rate_factor_max_increment ) );
    double q0 = q;

    /* B-frames are not directly subject to VBV,
     * since they are controlled by the P-frames' QPs. */

    if( rcc->b_vbv && rcc->last_satd > 0 )
    {
        double fenc_cpb_duration = (double)h->fenc->i_cpb_duration *
                                   h->sps->vui.i_num_units_in_tick / h->sps->vui.i_time_scale;
        /* Lookahead VBV: raise the quantizer as necessary such that no frames in
         * the lookahead overflow and such that the buffer is in a reasonable state
         * by the end of the lookahead. */
        if( h->param.rc.i_lookahead )      // rc-lookahead
        {
            int terminate = 0;

            /* Avoid an infinite loop. */
            for( int iterations = 0; iterations < 1000 && terminate != 3; iterations++ )
            {
                double frame_q[3];
                double cur_bits = predict_size( &rcc->pred[h->sh.i_type], q, rcc->last_satd );
                double buffer_fill_cur = rcc->buffer_fill - cur_bits;
                double target_fill;
                double total_duration = 0;
                double last_duration = fenc_cpb_duration;
                frame_q[0] = h->sh.i_type == SLICE_TYPE_I ? q * h->param.rc.f_ip_factor : q;
                frame_q[1] = frame_q[0] * h->param.rc.f_pb_factor;
                frame_q[2] = frame_q[0] / h->param.rc.f_ip_factor;

                /* Loop over the planned future frames. */
                //! look ahead frames: buffer消耗为结束条件
                for( int j = 0; buffer_fill_cur >= 0 && buffer_fill_cur <= rcc->buffer_size; j++ )
                {
                    total_duration += last_duration;
                    buffer_fill_cur += rcc->vbv_max_rate * last_duration;
                    int i_type = h->fenc->i_planned_type[j];
                    int i_satd = h->fenc->i_planned_satd[j];
                    if( i_type == X264_TYPE_AUTO )
                        break;
                    i_type = IS_X264_TYPE_I( i_type ) ? SLICE_TYPE_I : IS_X264_TYPE_B( i_type ) ? SLICE_TYPE_B : SLICE_TYPE_P;
                    //! qscale预测消耗bits
                    cur_bits = predict_size( &rcc->pred[i_type], frame_q[i_type], i_satd );
                    buffer_fill_cur -= cur_bits;
                    last_duration = h->fenc->f_planned_cpb_duration[j];
                }
                //! 50%<, >80%, 调整qscale
                /* Try to get to get the buffer at least 50% filled, but don't set an impossible goal. */
                target_fill = X264_MIN( rcc->buffer_fill + total_duration * rcc->vbv_max_rate * 0.5, rcc->buffer_size * 0.5 );
                if( buffer_fill_cur < target_fill )
                {
                    q *= 1.01;
                    terminate |= 1;
                    continue;
                }
                /* Try to get the buffer no more than 80% filled, but don't set an impossible goal. */
                target_fill = x264_clip3f( rcc->buffer_fill - total_duration * rcc->vbv_max_rate * 0.5, rcc->buffer_size * 0.8, rcc->buffer_size );
                if( rcc->b_vbv_min_rate && buffer_fill_cur > target_fill )
                {
                    q /= 1.01;
                    terminate |= 2;
                    continue;
                }
                break;
            }
        }
        /* Fallback to old purely-reactive algorithm: no lookahead. */
        else
        {
            if( ( pict_type == SLICE_TYPE_P ||
                ( pict_type == SLICE_TYPE_I && rcc->last_non_b_pict_type == SLICE_TYPE_I ) ) &&
                rcc->buffer_fill/rcc->buffer_size < 0.5 )
            {
                q /= x264_clip3f( 2.0*rcc->buffer_fill/rcc->buffer_size, 0.5, 1.0 );
            }

            /* Now a hard threshold to make sure the frame fits in VBV.
             * This one is mostly for I-frames. */
            double bits = predict_size( &rcc->pred[h->sh.i_type], q, rcc->last_satd );
            /* For small VBVs, allow the frame to use up the entire VBV. */
            double max_fill_factor = h->param.rc.i_vbv_buffer_size >= 5*h->param.rc.i_vbv_max_bitrate / rcc->fps ? 2 : 1;
            /* For single-frame VBVs, request that the frame use up the entire VBV. */
            double min_fill_factor = rcc->single_frame_vbv ? 1 : 2;

            if( bits > rcc->buffer_fill/max_fill_factor )
            {
                double qf = x264_clip3f( rcc->buffer_fill/(max_fill_factor*bits), 0.2, 1.0 );
                q /= qf;
                bits *= qf;
            }
            if( bits < rcc->buffer_rate/min_fill_factor )
            {
                double qf = x264_clip3f( bits*min_fill_factor/rcc->buffer_rate, 0.001, 1.0 );
                q *= qf;
            }
            q = X264_MAX( q0, q );
        }

        /* Check B-frame complexity, and use up any bits that would
         * overflow before the next P-frame. */
        if( h->sh.i_type == SLICE_TYPE_P && !rcc->single_frame_vbv )
        {
            int nb = rcc->bframes;
            double bits = predict_size( &rcc->pred[h->sh.i_type], q, rcc->last_satd );
            double pbbits = bits;
            double bbits = predict_size( rcc->pred_b_from_p, q * h->param.rc.f_pb_factor, rcc->last_satd );
            double space;
            double bframe_cpb_duration = 0;
            double minigop_cpb_duration;
            for( int i = 0; i < nb; i++ )
                bframe_cpb_duration += h->fenc->f_planned_cpb_duration[i];

            if( bbits * nb > bframe_cpb_duration * rcc->vbv_max_rate )
                nb = 0;
            pbbits += nb * bbits;

            minigop_cpb_duration = bframe_cpb_duration + fenc_cpb_duration;
            space = rcc->buffer_fill + minigop_cpb_duration*rcc->vbv_max_rate - rcc->buffer_size;
            if( pbbits < space )
            {
                q *= X264_MAX( pbbits / space, bits / (0.5 * rcc->buffer_size) );
            }
            q = X264_MAX( q0/2, q );
        }

        /* Apply MinCR and buffer fill restrictions */
        double bits = predict_size( &rcc->pred[h->sh.i_type], q, rcc->last_satd );
        double frame_size_maximum = X264_MIN( rcc->frame_size_maximum, X264_MAX( rcc->buffer_fill, 0.001 ) );
        if( bits > frame_size_maximum )
            q *= bits / frame_size_maximum;

        if( !rcc->b_vbv_min_rate )
            q = X264_MAX( q0, q );
    }

    if( lmin==lmax )
        return lmin;
    else if( rcc->b_2pass )
    {
        double min2 = log( lmin );
        double max2 = log( lmax );
        q = (log(q) - min2)/(max2-min2) - 0.5;
        q = 1.0/(1.0 + exp( -4*q ));
        q = q*(max2-min2) + min2;
        return exp( q );
    }
    else
        return x264_clip3f( q, lmin, lmax );
}

// update VBV after encoding a frame
static int update_vbv( x264_t *h, int bits )
{
    int filler = 0;
    int bitrate = h->sps->vui.hrd.i_bit_rate_unscaled;
    x264_ratecontrol_t *rcc = h->rc;
    x264_ratecontrol_t *rct = h->thread[0]->rc;
    int64_t buffer_size = (int64_t)h->sps->vui.hrd.i_cpb_size_unscaled * h->sps->vui.i_time_scale;

    if( rcc->last_satd >= h->mb.i_mb_count )
        update_predictor( &rct->pred[h->sh.i_type], qp2qscale( rcc->qpa_rc ), rcc->last_satd, bits );

    if( !rcc->b_vbv )
        return filler;

    uint64_t buffer_diff = (uint64_t)bits * h->sps->vui.i_time_scale;
    rct->buffer_fill_final -= buffer_diff;
    rct->buffer_fill_final_min -= buffer_diff;

    if( rct->buffer_fill_final_min < 0 )
    {
        double underflow = (double)rct->buffer_fill_final_min / h->sps->vui.i_time_scale;
        if( rcc->rate_factor_max_increment && rcc->qpm >= rcc->qp_novbv + rcc->rate_factor_max_increment )
            x264_log( h, X264_LOG_DEBUG, "VBV underflow due to CRF-max (frame %d, %.0f bits)\n", h->i_frame, underflow );
        else
            x264_log( h, X264_LOG_WARNING, "VBV underflow (frame %d, %.0f bits)\n", h->i_frame, underflow );
        rct->buffer_fill_final =
        rct->buffer_fill_final_min = 0;
    }

    if( h->param.i_avcintra_class )
        buffer_diff = buffer_size;
    else
        buffer_diff = (uint64_t)bitrate * h->sps->vui.i_num_units_in_tick * h->fenc->i_cpb_duration;
    rct->buffer_fill_final += buffer_diff;
    rct->buffer_fill_final_min += buffer_diff;

    if( rct->buffer_fill_final > buffer_size )
    {
        if( h->param.rc.b_filler )
        {
            int64_t scale = (int64_t)h->sps->vui.i_time_scale * 8;
            filler = (rct->buffer_fill_final - buffer_size + scale - 1) / scale;
            bits = h->param.i_avcintra_class ? filler * 8 : X264_MAX( (FILLER_OVERHEAD - h->param.b_annexb), filler ) * 8;
            buffer_diff = (uint64_t)bits * h->sps->vui.i_time_scale;
            rct->buffer_fill_final -= buffer_diff;
            rct->buffer_fill_final_min -= buffer_diff;
        }
        else
        {
            rct->buffer_fill_final = X264_MIN( rct->buffer_fill_final, buffer_size );
            rct->buffer_fill_final_min = X264_MIN( rct->buffer_fill_final_min, buffer_size );
        }
    }

    return filler;
}