[Dogway]

Can somebody help me to speed up this script? I tweaked mcawarpsharp a bit for speed and control but this run at around 0.15fps on a 720x480 clip with 96000 frames. I think the bottleneck is at mflow in the 4x supsampled clip but I'd like to know if I can speed up that part or others as well without using a smaller supsampling.

setmtmode(5,2)
ffvideoSource("FFV1intermediary.avi")
a=last
setmtmode(2,2)


white=70
mt_edge("min/max",thY1=0,thY2=255).removegrain(11).mt_expand.mt_expand.mt_lut("x "+string(white)+" > 255 x "+string(white)+" / 255 * ?")

BicubicResize (180,120, 1, 0)
TemporalSoften(10,30,0,15,2)
BicubicResize (720,480, 1, 0)
global edgemask=last

deconv_v =  "-3 10 4 -4 8 -6 100 -6 8 -4 4 10 -3"
mt_merge(a,a.mt_convolution(horizontal="1",vertical=deconv_v, Y=3, U=2, V=2),edgemask,u=4,v=4)

MCaWarpSharp4(4,2,0.6,true,640,360)

smdegrain(tr=3,thSAD=400,hpad=0,vpad=0,chroma=false,plane=0)



function MCaWarpSharp4(clip source, int "supsamp",int "post", float "PPstr", bool "fast", int "w", int "h"){

supsamp = default(supsamp, 4)	# supsamp=2 recommended for testing, supsamp=4 for encoding.
post    = default(post, 4)      # mix the warpsharped edges with original footage thru blur and sharpen post processing
str     = default(PPstr,1.0)
fast    = default(fast,true)
w       = default(w,source.width())
h       = default(h,source.height())


var=32*pow(supsamp,-2)
w1=source.width()*supsamp
h1=source.height()*supsamp

source
sourceSup=fast ? bicubicResize(w1,h1,b=0.0,c=0.5) : nnedi3_rpow2(rfactor=supsamp,cshift="spline64resize",nns=4,qual=2)

WarpedEdges=sourceSup.aWarpSharp2(
\ thresh=int(255*pow(supsamp,-0.207)),
\ blur=3*int(pow(supsamp,1.7925)),
\ type=1,depth=8*int(pow(supsamp,1.7925)),chroma=4)

Interleave(sourceSup,WarpedEdges)

blurredclip=GaussResize(w1*2,h1*2,p=var).GaussResize(w1,h1,p=var)

super  =          MSuper(blurredclip, levels=1, pel=fast?1:2, sharp=fast?0:2)
super2 =          MSuper(levels=1, pel=fast?1:2, sharp=fast?0:2)
forward_vectors = MAnalyse(super, blksize=4, levels=1, search=3, searchparam=5, isb=true)
                  MFlow(super2,forward_vectors)

SelectEvery(2,0)
fast ? bicubicResize(w,h,b=0.0,c=0.5) : Spline36Resize(w,h)

# Replacing 'bad' edges with 'good' edges on the original image
source    = post==1 && (Defined(w) || Defined(h)) ? (fast ? source.bicubicResize(w1,h1,b=0.0,c=0.5) : source.Spline36Resize(w1,h1)) : source
#~ edgemask  = source.mt_edge("min/max").blur(1.0)

Assert  ((post >= 1 && post <= 4 )  ? true : false, chr(10) + "'post' have not a correct value! [1,2,3,4]" + chr(10))
post =   (post==1) ? mt_merge(source,last,edgemask.bilinearresize(w,h),luma=true)
    \  : (post==2) ? mt_merge(Blur(min(str*0.5,1.58)),edgemask.bilinearresize(w,h),luma=true)
    \  : (post==3) ? mt_merge(LSFmod(defaults=fast?"fast":"slow",strength=int(str*20),edgemode=0,soothe=true,ss_x=1.0,ss_y=1.0),last,edgemask.bilinearresize(w,h),luma=true)
    \  : (post==4) ? mt_merge(LSFmod(defaults=fast?"fast":"slow",strength=int(str*20),edgemode=0,soothe=true,ss_x=1.0,ss_y=1.0),Blur(min(str*0.5,1.58)),edgemask.bilinearresize(w,h),luma=true)
    \  :  blankclip(source, width=width, height=120).SubTitle("post = " + string(post),text_color=$FFFFFF,font="COURIER NEW",size=12,x=320,y=90)
return post}

edit: I tweaked the manalyse portion of the mcawarpsharp4 function with the new mscalevectors from cretindesalpes, but results are no good, I can't go sub 4 for blksize so I don't know if that's the reason, also mode=2 doesn't work, so I couldn't check.

function MCaWarpSharp4(clip source, int "supsamp",int "post", float "PPstr", bool "fast", int "w", int "h"){

supsamp = default(supsamp, 4)	# supsamp=2 recommended for testing, supsamp=4 for encoding.
post    = default(post, 4)      # mix the warpsharped edges with original footage thru blur and sharpen post processing
str     = default(PPstr,1.0)
fast    = default(fast,true)
w       = default(w,source.width())
h       = default(h,source.height())


var=32*pow(supsamp,-2)
w1=source.width()*supsamp
h1=source.height()*supsamp

source
sourceSup=fast ? bicubicResize(w1,h1,b=0.0,c=0.5) : nnedi3_rpow2(rfactor=supsamp,cshift="spline64resize",nns=4,qual=2)

WarpedEdges=sourceSup.aWarpSharp2(
\ thresh=int(255*pow(supsamp,-0.207)),
\ blur=3*int(pow(supsamp,1.7925)),
\ type=1,depth=8*int(pow(supsamp,1.7925)),chroma=4)

Interleave(sourceSup,WarpedEdges)

blurredclip=GaussResize(w1*2,h1*2,p=var).GaussResize(720,480,p=32*pow(1,-2))

super  =          MSuper(blurredclip, levels=1, pel=fast?1:2, sharp=fast?0:2,hpad=0,vpad=0)
super2 =          MSuper(levels=1, pel=fast?1:2, sharp=fast?0:2,hpad=0,vpad=0)
forward_vectors = MAnalyse(super, blksize=4, levels=1, search=3, searchparam=5, isb=true).MScaleVect(4)
                  MFlow(super2,forward_vectors)

SelectEvery(2,0)
fast ? bicubicResize(w,h,b=0.0,c=0.5) : Spline36Resize(w,h)

# Replacing 'bad' edges with 'good' edges on the original image
source    = post==1 && (Defined(w) || Defined(h)) ? (fast ? source.bicubicResize(w1,h1,b=0.0,c=0.5) : source.Spline36Resize(w1,h1)) : source
#~ edgemask  = source.mt_edge("min/max").blur(1.0)

Assert  ((post >= 1 && post <= 4 )  ? true : false, chr(10) + "'post' have not a correct value! [1,2,3,4]" + chr(10))
post =   (post==1) ? mt_merge(source,last,edgemask.bilinearresize(w,h),luma=true)
    \  : (post==2) ? mt_merge(Blur(min(str*0.5,1.58)),edgemask.bilinearresize(w,h),luma=true)
    \  : (post==3) ? mt_merge(LSFmod(defaults=fast?"fast":"slow",strength=int(str*20),edgemode=0,soothe=true,ss_x=1.0,ss_y=1.0),last,edgemask.bilinearresize(w,h),luma=true)
    \  : (post==4) ? mt_merge(LSFmod(defaults=fast?"fast":"slow",strength=int(str*20),edgemode=0,soothe=true,ss_x=1.0,ss_y=1.0),Blur(min(str*0.5,1.58)),edgemask.bilinearresize(w,h),luma=true)
    \  :  blankclip(source, width=width, height=120).SubTitle("post = " + string(post),text_color=$FFFFFF,font="COURIER NEW",size=12,x=320,y=90)
return post}