q0  = q0low;        } else if (q1 > q1high) {            q0 -= q1 - q1high;            q1  = q1high;        }    }    // q0 == q1 isn't really a legal situation    if (q0 == q1) {        // the following is indirect but guarantees q1 != q0 && q1 near q0        q1 = av_clip(q0+1, 1, SCALE_MAX_POS);        q0 = av_clip(q1-1, 0, SCALE_MAX_POS - 1);    }     for (i = 0; i < TRELLIS_STATES; i++) {        paths[0][i].cost    = 0.0f;        paths[0][i].prev    = -1;    }    for (j = 1; j < TRELLIS_STAGES; j++) {        for (i = 0; i < TRELLIS_STATES; i++) {            paths[j][i].cost    = INFINITY;            paths[j][i].prev    = -2;        }    }    idx = 1;    s->aacdsp.abs_pow34(s->scoefs, sce->coeffs, 1024);    for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w]) {        start = w*128;        for (g = 0; g < sce->ics.num_swb; g++) {            const float *coefs = &sce->coeffs[start];            float qmin, qmax;            int nz = 0;             bandaddr[idx] = w * 16 + g;            qmin = INT_MAX;            qmax = 0.0f;            for (w2 = 0; w2 < sce->ics.group_len[w]; w2++) {                FFPsyBand *band = &s->psy.ch[s->cur_channel].psy_bands[(w+w2)*16+g];                if (band->energy <= band->threshold || band->threshold == 0.0f) {                    sce->zeroes[(w+w2)*16+g] = 1;                    continue;                }                sce->zeroes[(w+w2)*16+g] = 0;                nz = 1;                for (i = 0; i < sce->ics.swb_sizes[g]; i++) {                    float t = fabsf(coefs[w2*128+i]);                    if (t > 0.0f)                        qmin = FFMIN(qmin, t);                    qmax = FFMAX(qmax, t);                }            }            if (nz) {                int minscale, maxscale;                float minrd = INFINITY;                float maxval;                //minimum scalefactor index is when minimum nonzero coefficient after quantizing is not clipped                minscale = coef2minsf(qmin);                //maximum scalefactor index is when maximum coefficient after quantizing is still not zero                maxscale = coef2maxsf(qmax);                minscale = av_clip(minscale - q0, 0, TRELLIS_STATES - 1);                maxscale = av_clip(maxscale - q0, 0, TRELLIS_STATES);                if (minscale == maxscale) {                    maxscale = av_clip(minscale+1, 1, TRELLIS_STATES);                    minscale = av_clip(maxscale-1, 0, TRELLIS_STATES - 1);                }                maxval = find_max_val(sce->ics.group_len[w], sce->ics.swb_sizes[g], s->scoefs+start);                for (q = minscale; q < maxscale; q++) {                    float dist = 0;                    int cb = find_min_book(maxval, sce->sf_idx[w*16+g]);                    for (w2 = 0; w2 < sce->ics.group_len[w]; w2++) {                        FFPsyBand *band = &s->psy.ch[s->cur_channel].psy_bands[(w+w2)*16+g];                        dist += quantize_band_cost(s, coefs + w2*128, s->scoefs + start + w2*128, sce->ics.swb_sizes[g],                                                   q + q0, cb, lambda / band->threshold, INFINITY, NULL, NULL);                    }                    minrd = FFMIN(minrd, dist);                     for (i = 0; i < q1 - q0; i++) {                        float cost;                        cost = paths[idx - 1][i].cost + dist                               + ff_aac_scalefactor_bits[q - i + SCALE_DIFF_ZERO];                        if (cost < paths[idx][q].cost) {                            paths[idx][q].cost    = cost;                            paths[idx][q].prev    = i;                        }                    }                }            } else {                for (q = 0; q < q1 - q0; q++) {                    paths[idx][q].cost = paths[idx - 1][q].cost + 1;                    paths[idx][q].prev = q;                }            }            sce->zeroes[w*16+g] = !nz;            start += sce->ics.swb_sizes[g];            idx++;        }    }    idx--;    mincost = paths[idx][0].cost;    minq    = 0;    for (i = 1; i < TRELLIS_STATES; i++) {        if (paths[idx][i].cost < mincost) {            mincost = paths[idx][i].cost;            minq = i;        }    }    while (idx) {        sce->sf_idx[bandaddr[idx]] = minq + q0;        minq = FFMAX(paths[idx][minq].prev, 0);        idx--;    }    //set the same quantizers inside window groups    for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w])        for (g = 0; g < sce->ics.num_swb; g++)            for (w2 = 1; w2 < sce->ics.group_len[w]; w2++)                sce->sf_idx[(w+w2)*16+g] = sce->sf_idx[w*16+g];} static void search_for_quantizers_fast(AVCodecContext *avctx, AACEncContext *s,                                       SingleChannelElement *sce,                                       const float lambda){    int start = 0, i, w, w2, g;    int destbits = avctx->bit_rate * 1024.0 / avctx->sample_rate / avctx->ch_layout.nb_channels * (lambda / 120.f);    float dists[128] = { 0 }, uplims[128] = { 0 };    float maxvals[128];    int fflag, minscaler;    int its  = 0;    int allz = 0;    float minthr = INFINITY;     // for values above this the decoder might end up in an endless loop    // due to always having more bits than what can be encoded.    destbits = FFMIN(destbits, 5800);    //some heuristic to determine initial quantizers will reduce search time    //determine zero bands and upper limits    for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w]) {        start = 0;        for (g = 0; g < sce->ics.num_swb; g++) {            int nz = 0;            float uplim = 0.0f;            for (w2 = 0; w2 < sce->ics.group_len[w]; w2++) {                FFPsyBand *band = &s->psy.ch[s->cur_channel].psy_bands[(w+w2)*16+g];                uplim += band->threshold;                if (band->energy <= band->threshold || band->threshold == 0.0f) {                    sce->zeroes[(w+w2)*16+g] = 1;                    continue;                }                nz = 1;            }            uplims[w*16+g] = uplim *512;            sce->band_type[w*16+g] = 0;            sce->zeroes[w*16+g] = !nz;            if (nz)                minthr = FFMIN(minthr, uplim);            allz |= nz;            start += sce->ics.swb_sizes[g];        }    }    for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w]) {        for (g = 0; g < sce->ics.num_swb; g++) {            if (sce->zeroes[w*16+g]) {                sce->sf_idx[w*16+g] = SCALE_ONE_POS;                continue;            }            sce->sf_idx[w*16+g] = SCALE_ONE_POS + FFMIN(log2f(uplims[w*16+g]/minthr)*4,59);        }    }     if (!allz)        return;    s->aacdsp.abs_pow34(s->scoefs, sce->coeffs, 1024);    ff_quantize_band_cost_cache_init(s);     for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w]) {        start = w*128;        for (g = 0; g < sce->ics.num_swb; g++) {            const float *scaled = s->scoefs + start;            maxvals[w*16+g] = find_max_val(sce->ics.group_len[w], sce->ics.swb_sizes[g], scaled);            start += sce->ics.swb_sizes[g];        }    }     //perform two-loop search    //outer loop - improve quality    do {        int tbits, qstep;        minscaler = sce->sf_idx[0];        //inner loop - quantize spectrum to fit into given number of bits        qstep = its ? 1 : 32;        do {            int prev = -1;            tbits = 0;            for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w]) {                start = w*128;                for (g = 0; g < sce->ics.num_swb; g++) {                    const float *coefs = sce->coeffs + start;                    const float *scaled = s->scoefs + start;                    int bits = 0;                    int cb;                    float dist = 0.0f;                     if (sce->zeroes[w*16+g] || sce->sf_idx[w*16+g] >= 218) {                        start += sce->ics.swb_sizes[g];                        continue;                    }                    minscaler = FFMIN(minscaler, sce->sf_idx[w*16+g]);                    cb = find_min_book(maxvals[w*16+g], sce->sf_idx[w*16+g]);                    for (w2 = 0; w2 < sce->ics.group_len[w]; w2++) {                        int b;                        dist += quantize_band_cost_cached(s, w + w2, g,                                                          coefs + w2*128,                                                          scaled + w2*128,                                                          sce->ics.swb_sizes[g],                                                          sce->sf_idx[w*16+g],                                                          cb, 1.0f, INFINITY,                                                          &b, NULL, 0);                        bits += b;                    }                    dists[w*16+g] = dist - bits;                    if (prev != -1) {                        bits += ff_aac_scalefactor_bits[sce->sf_idx[w*16+g] - prev + SCALE_DIFF_ZERO];                    }                    tbits += bits;                    start += sce->ics.swb_sizes[g];                    prev = sce->sf_idx[w*16+g];                }            }            if (tbits > destbits) {                for (i = 0; i < 128; i++)                    if (sce->sf_idx[i] < 218 - qstep)                        sce->sf_idx[i] += qstep;            } else {                for (i = 0; i < 128; i++)                    if (sce->sf_idx[i] > 60 - qstep)                        sce->sf_idx[i] -= qstep;            }            qstep >>= 1;            if (!qstep && tbits > destbits*1.02 && sce->sf_idx[0] < 217)                qstep = 1;        } while (qstep);         fflag = 0;        minscaler = av_clip(minscaler, 60, 255 - SCALE_MAX_DIFF);         for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w]) {            for (g = 0; g < sce->ics.num_swb; g++) {                int prevsc = sce->sf_idx[w*16+g];                if (dists[w*16+g] > uplims[w*16+g] && sce->sf_idx[w*16+g] > 60) {                    if (find_min_book(maxvals[w*16+g], sce->sf_idx[w*16+g]-1))                        sce->sf_idx[w*16+g]--;                    else //Try to make sure there is some energy in every band                        sce->sf_idx[w*16+g]-=2;                }                sce->sf_idx[w*16+g] = av_clip(sce->sf_idx[w*16+g], minscaler, minscaler + SCALE_MAX_DIFF);                sce->sf_idx[w*16+g] = FFMIN(sce->sf_idx[w*16+g], 219);                if (sce->sf_idx[w*16+g] != prevsc)                    fflag = 1;                sce->band_type[w*16+g] = find_min_book(maxvals[w*16+g], sce->sf_idx[w*16+g]);            }        }        its++;    } while (fflag && its < 10);} static void search_for_pns(AACEncContext *s, AVCodecContext *avctx, SingleChannelElement *sce){    FFPsyBand *band;    int w, g, w2, i;    int wlen = 1024 / sce->ics.num_windows;    int bandwidth, cutoff;    float *PNS = &s->scoefs[0*128], *PNS34 = &s->scoefs[1*128];    float *NOR34 = &s->scoefs[3*128];    uint8_t nextband[128];    const float lambda = s->lambda;    const float freq_mult = avctx->sample_rate*0.5f/wlen;    const float thr_mult = NOISE_LAMBDA_REPLACE*(100.0f/lambda);    const float spread_threshold = FFMIN(0.75f, NOISE_SPREAD_THRESHOLD*FFMAX(0.5f, lambda/100.f));    const float dist_bias = av_clipf(4.f * 120 / lambda, 0.25f, 4.0f);    const float pns_transient_energy_r = FFMIN(0.7f, lambda / 140.f);     int refbits = avctx->bit_rate * 1024.0 / avctx->sample_rate        / ((avctx->flags & AV_CODEC_FLAG_QSCALE) ? 2.0f : avctx->ch_layout.nb_channels)        * (lambda / 120.f);     /** Keep this in sync with twoloop's cutoff selection */    float rate_bandwidth_multiplier = 1.5f;    int prev = -1000, prev_sf = -1;    int frame_bit_rate = (avctx->flags & AV_CODEC_FLAG_QSCALE)        ? (refbits * rate_bandwidth_multiplier * avctx->sample_rate / 1024)        : (avctx->bit_rate / avctx->ch_layout.nb_channels);     frame_bit_rate *= 1.15f;     if (avctx->cutoff > 0) {        bandwidth = avctx->cutoff;    } else {        bandwidth = FFMAX(3000, AAC_CUTOFF_FROM_BITRATE(frame_bit_rate, 1, avctx->sample_rate));    }     cutoff = bandwidth * 2 * wlen / avctx->sample_rate;     memcpy(sce->band_alt, sce->band_type, sizeof(sce->band_type));    ff_init_nextband_map(sce, nextband);    for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w]) {        int wstart = w*128;        for (g = 0; g < sce->ics.num_swb; g++) {            int noise_sfi;            float dist1 = 0.0f, dist2 = 0.0f, noise_amp;            float pns_energy = 0.0f, pns_tgt_energy, energy_ratio, dist_thresh;            float sfb_energy = 0.0f, threshold = 0.0f, spread = 2.0f;            float min_energy = -1.0f, max_energy = 0.0f;            const int start = wstart+sce->ics.swb_offset[g];            const float freq = (start-wstart)*freq_mult;            const float freq_boost = FFMAX(0.88f*freq/NOISE_LOW_LIMIT, 1.0f);            if (freq < NOISE_LOW_LIMIT || (start-wstart) >= cutoff) {                if (!sce->zeroes[w*16+g])                    prev_sf = sce->sf_idx[w*16+g];                continue;            }            for (w2 = 0; w2 < sce->ics.group_len[w]; w2++) {                band = &s->psy.ch[s->cur_channel].psy_bands[(w+w2)*16+g];                sfb_energy += band->energy;                spread     = FFMIN(spread, band->spread);                threshold  += band->threshold;                if (!w2) {                    min_energy = max_energy = band->energy;                } else {                    min_energy = FFMIN(min_energy, band->energy);                    max_energy = FFMAX(max_energy, band->energy);                }            }             /* Ramps down at ~8000Hz and loosens the dist threshold */            dist_thresh = av_clipf(2.5f*NOISE_LOW_LIMIT/freq, 0.5f, 2.5f) * dist_bias;             /* PNS is acceptable when all of these are true:             * 1. high spread energy (noise-like band)             * 2. near-threshold energy (high PE means the random nature of PNS content will be noticed)             * 3. on short window groups, all windows have similar energy (variations in energy would be destroyed by PNS)             *             * At this stage, point 2 is relaxed for zeroed bands near the noise threshold (hole avoidance is more important)             */            if ((!sce->zeroes[w*16+g] && !ff_sfdelta_can_remove_band(sce, nextband, prev_sf, w*16+g)) ||                ((sce->zeroes[w*16+g] || !sce->band_alt[w*16+g]) && sfb_energy < threshold*sqrtf(1.0f/freq_boost)) || spread < spread_threshold ||                (!sce->zeroes[w*16+g] && sce->band_alt[w*16+g] && sfb_energy > threshold*thr_mult*freq_boost) ||                min_energy < pns_transient_energy_r * max_energy ) {                sce->pns_ener[w*16+g] = sfb_energy;                if (!sce->zeroes[w*16+g])                    prev_sf = sce->sf_idx[w*16+g];                continue;            }             pns_tgt_energy = sfb_energy*FFMIN(1.0f, spread*spread);            noise_sfi = av_clip(roundf(log2f(pns_tgt_energy)*2), -100, 155); /* Quantize */            noise_amp = -ff_aac_pow2sf_tab[noise_sfi + POW_SF2_ZERO];    /* Dequantize */            if (prev != -1000) {                int noise_sfdiff = noise_sfi - prev + SCALE_DIFF_ZERO;                if (noise_sfdiff < 0 || noise_sfdiff > 2*SCALE_MAX_DIFF) {                    if (!sce->zeroes[w*16+g])                        prev_sf = sce->sf_idx[w*16+g];                    continue;                }            }            for (w2 = 0; w2 < sce->ics.group_len[w]; w2++) {                float band_energy, scale, pns_senergy;                const int start_c = (w+w2)*128+sce->ics.swb_offset[g];                band = &s->psy.ch[s->cur_channel].psy_bands[(w+w2)*16+g];                for (i = 0; i < sce->ics.swb_sizes[g]; i++) {                    s->random_state  = lcg_random(s->random_state);                    PNS[i] = s->random_state;                }                band_energy = s->fdsp->scalarproduct_float(PNS, PNS, sce->ics.swb_sizes[g]);                scale = noise_amp/sqrtf(band_energy);                s->fdsp->vector_fmul_scalar(PNS, PNS, scale, sce->ics.swb_sizes[g]);                pns_senergy = s->fdsp->scalarproduct_float(PNS, PNS, sce->ics.swb_sizes[g]);                pns_energy += pns_senergy;                s->aacdsp.abs_pow34(NOR34, &sce->coeffs[start_c], sce->ics.swb_sizes[g]);                s->aacdsp.abs_pow34(PNS34, PNS, sce->ics.swb_sizes[g]);                dist1 += quantize_band_cost(s, &sce->coeffs[start_c],                                            NOR34,                                            sce->ics.swb_sizes[g],                                            sce->sf_idx[(w+w2)*16+g],                                            sce->band_alt[(w+w2)*16+g],                                            lambda/band->threshold, INFINITY, NULL, NULL);                /* Estimate rd on average as 5 bits for SF, 4 for the CB, plus spread energy * lambda/thr */                dist2 += band->energy/(band->spread*band->spread)*lambda*dist_thresh/band->threshold;            }            if (g && sce->band_type[w*16+g-1] == NOISE_BT) {                dist2 += 5;            } else {                dist2 += 9;            }            energy_ratio = pns_tgt_energy/pns_energy; /* Compensates for quantization error */            sce->pns_ener[w*16+g] = energy_ratio*pns_tgt_energy;            if (sce->zeroes[w*16+g] || !sce->band_alt[w*16+g] || (energy_ratio > 0.85f && energy_ratio < 1.25f && dist2 < dist1)) {                sce->band_type[w*16+g] = NOISE_BT;                sce->zeroes[w*16+g] = 0;                prev = noise_sfi;            } else {                if (!sce->zeroes[w*16+g])                    prev_sf = sce->sf_idx[w*16+g];            }        }    }} static void mark_pns(AACEncContext *s, AVCodecContext *avctx, SingleChannelElement *sce){    FFPsyBand *band;    int w, g, w2;    int wlen = 1024 / sce->ics.num_windows;    int bandwidth, cutoff;    const float lambda = s->lambda;    const float freq_mult = avctx->sample_rate*0.5f/wlen;    const float spread_threshold = FFMIN(0.75f, NOISE_SPREAD_THRESHOLD*FFMAX(0.5f, lambda/100.f));    const float pns_transient_energy_r = FFMIN(0.7f, lambda / 140.f);     int refbits = avctx->bit_rate * 1024.0 / avctx->sample_rate        / ((avctx->flags & AV_CODEC_FLAG_QSCALE) ? 2.0f : avctx->ch_layout.nb_channels)        * (lambda / 120.f);     /** Keep this in sync with twoloop's cutoff selection */    float rate_bandwidth_multiplier = 1.5f;    int frame_bit_rate = (avctx->flags & AV_CODEC_FLAG_QSCALE)        ? (refbits * rate_bandwidth_multiplier * avctx->sample_rate / 1024)        : (avctx->bit_rate / avctx->ch_layout.nb_channels);     frame_bit_rate *= 1.15f;     if (avctx->cutoff > 0) {        bandwidth = avctx->cutoff;    } else {        bandwidth = FFMAX(3000, AAC_CUTOFF_FROM_BITRATE(frame_bit_rate, 1, avctx->sample_rate));    }     cutoff = bandwidth * 2 * wlen / avctx->sample_rate;     memcpy(sce->band_alt, sce->band_type, sizeof(sce->band_type));    for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w]) {        for (g = 0; g < sce->ics.num_swb; g++) {            float sfb_energy = 0.0f, threshold = 0.0f, spread = 2.0f;            float min_energy = -1.0f, max_energy = 0.0f;            const int start = sce->ics.swb_offset[g];            const float freq = start*freq_mult;            const float freq_boost = FFMAX(0.88f*freq/NOISE_LOW_LIMIT, 1.0f);            if (freq < NOISE_LOW_LIMIT || start >= cutoff) {                sce->can_pns[w*16+g] = 0;                continue;            }            for (w2 = 0; w2 < sce->ics.group_len[w]; w2++) {                band = &s->psy.ch[s->cur_channel].psy_bands[(w+w2)*16+g];                sfb_energy += band->energy;                spread     = FFMIN(spread, band->spread);                threshold  += band->threshold;                if (!w2) {                    min_energy = max_energy = band->energy;                } else {                    min_energy = FFMIN(min_energy, band->energy);                    max_energy = FFMAX(max_energy, band->energy);                }            }             /* PNS is acceptable when all of these are true:             * 1. high spread energy (noise-like band)             * 2. near-threshold energy (high PE means the random nature of PNS content will be noticed)             * 3. on short window groups, all windows have similar energy (variations in energy would be destroyed by PNS)             */            sce->pns_ener[w*16+g] = sfb_energy;            if (sfb_energy < threshold*sqrtf(1.5f/freq_boost) || spread < spread_threshold || min_energy < pns_transient_energy_r * max_energy) {                sce->can_pns[w*16+g] = 0;            } else {                sce->can_pns[w*16+g] = 1;            }        }    }} static void search_for_ms(AACEncContext *s, ChannelElement *cpe){    int start = 0, i, w, w2, g, sid_sf_boost, prev_mid, prev_side;    uint8_t nextband0[128], nextband1[128];    float *M   = s->scoefs + 128*0, *S   = s->scoefs + 128*1;    float *L34 = s->scoefs + 128*2, *R34 = s->scoefs + 128*3;    float *M34 = s->scoefs + 128*4, *S34 = s->scoefs + 128*5;    const float lambda = s->lambda;    const float mslambda = FFMIN(1.0f, lambda / 120.f);    SingleChannelElement *sce0 = &cpe->ch[0];    SingleChannelElement *sce1 = &cpe->ch[1];    if (!cpe->common_window)        return;     /** Scout out next nonzero bands */    ff_init_nextband_map(sce0, nextband0);    ff_init_nextband_map(sce1, nextband1);     prev_mid = sce0->sf_idx[0];    prev_side = sce1->sf_idx[0];    for (w = 0; w < sce0->ics.num_windows; w += sce0->ics.group_len[w]) {        start = 0;        for (g = 0; g < sce0->ics.num_swb; g++) {

Lines 501–1000 of 1186. Previous lines Load more