@@ -43,8 +43,7 @@ struct weighted_avg {
float sum;
};
-#define WEIGHT_LUT_NBITS 9
-#define WEIGHT_LUT_SIZE (1<<WEIGHT_LUT_NBITS)
+#define WEIGHT_LUT_SIZE (800000) // need to > 300 * 300 * log(255)
typedef struct NLMeansContext {
const AVClass *class;
@@ -63,7 +62,6 @@ typedef struct NLMeansContext {
struct weighted_avg *wa; // weighted average of every pixel
ptrdiff_t wa_linesize; // linesize for wa in struct size unit
float weight_lut[WEIGHT_LUT_SIZE]; // lookup table mapping (scaled) patch differences to their associated weights
- float pdiff_lut_scale; // scale factor for patch differences before looking into the LUT
uint32_t max_meaningful_diff; // maximum difference considered (if the patch difference is too high we ignore the pixel)
NLMeansDSPContext dsp;
} NLMeansContext;
@@ -401,8 +399,7 @@ static int nlmeans_slice(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs
const uint32_t patch_diff_sq = e - d - b + a;
if (patch_diff_sq < s->max_meaningful_diff) {
- const unsigned weight_lut_idx = patch_diff_sq * s->pdiff_lut_scale;
- const float weight = s->weight_lut[weight_lut_idx]; // exp(-patch_diff_sq * s->pdiff_scale)
+ const float weight = s->weight_lut[patch_diff_sq]; // exp(-patch_diff_sq * s->pdiff_scale)
wa[x].total_weight += weight;
wa[x].sum += weight * src[x];
}
@@ -527,10 +524,9 @@ static av_cold int init(AVFilterContext *ctx)
s->pdiff_scale = 1. / (h * h);
s->max_meaningful_diff = -log(1/255.) / s->pdiff_scale;
- s->pdiff_lut_scale = 1./s->max_meaningful_diff * WEIGHT_LUT_SIZE;
- av_assert0((s->max_meaningful_diff - 1) * s->pdiff_lut_scale < FF_ARRAY_ELEMS(s->weight_lut));
+ av_assert0((s->max_meaningful_diff - 1) < FF_ARRAY_ELEMS(s->weight_lut));
for (i = 0; i < WEIGHT_LUT_SIZE; i++)
- s->weight_lut[i] = exp(-i / s->pdiff_lut_scale * s->pdiff_scale);
+ s->weight_lut[i] = exp(-i * s->pdiff_scale);
CHECK_ODD_FIELD(research_size, "Luma research window");
CHECK_ODD_FIELD(patch_size, "Luma patch");
Remove the pdiff_lut_scale in nlmeans, and this change will avoid using pdiff_lut_scale in the exp table search in nlmean_slice, it's will improve the performance about 12%. Use the profiling cmd like: perf stat -a -d -r 5 ./ffmpeg -i input -an -vf nlmeans=s=30 -vframes 10 \ -f null /dev/null without this change: when s=1.0(default value) 63s s=30.0 72s after this change: s=1.0(default value) 56s s=30.0 63s Signed-off-by: Jun Zhao <mypopydev@gmail.com> --- libavfilter/vf_nlmeans.c | 12 ++++-------- 1 files changed, 4 insertions(+), 8 deletions(-)