From: "Chris Zwar" <AE-List@media-motion.tv>
Content-Type: multipart/alternative;
	boundary="Apple-Mail=_3FA9B38F-0A08-44F0-8A7F-C3CE30167B8B"
Mime-Version: 1.0 (Mac OS X Mail 11.4 \(3445.8.2\))
Subject: nVidias Slo mo demo
Message-Id: <9BE7FAB4-CBE1-48B6-A980-1213588240E5@chriszwar.com>
Date: Wed, 20 Jun 2018 15:38:29 +1000
To: After Effects Mail List <AE-List@media-motion.tv>


--Apple-Mail=_3FA9B38F-0A08-44F0-8A7F-C3CE30167B8B
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain;
	charset=utf-8

Yesterday nVidia posted a demo of their slo-mo research, which uses AI / =
machine learning to dramatically slow down footage and interpolate =
between frames.

https://www.youtube.com/watch?time_continue=3D43&v=3DMjViy6kyiqs =
<https://www.youtube.com/watch?time_continue=3D43&v=3DMjViy6kyiqs>

I have to say that I don=E2=80=99t really see any advantage over =
existing optical flow technology (ie twixtor).  I did make the brave =
step of actually reading the YouTube comments, and a few people did =
mention twixtor with one person saying the nVidia version is =E2=80=9Cvast=
ly superior=E2=80=9D.  But I don=E2=80=99t see it.  Similar artefacts, =
lots of blurring, I just don=E2=80=99t see an immediate advantage over =
existing technology.  Of course it=E2=80=99s difficult to judge without =
access to the source footage itself.  Twixtor and comparable plugins can =
vary widely depending on the quality of the source footage, with things =
like noise/grain and compression artefacts sometimes being a make or =
break factor.  So maybe this new technology is more tolerant?

What do you think?

-Chris


--Apple-Mail=_3FA9B38F-0A08-44F0-8A7F-C3CE30167B8B
Content-Transfer-Encoding: quoted-printable
Content-Type: text/html;
	charset=utf-8

<html><head><meta http-equiv=3D"Content-Type" content=3D"text/html; =
charset=3Dutf-8"></head><body style=3D"word-wrap: break-word; =
-webkit-nbsp-mode: space; line-break: after-white-space;" =
class=3D"">Yesterday nVidia posted a demo of their slo-mo research, =
which uses AI / machine learning to dramatically slow down footage and =
interpolate between frames.<div class=3D""><br class=3D""></div><div =
class=3D""><a =
href=3D"https://www.youtube.com/watch?time_continue=3D43&amp;v=3DMjViy6kyi=
qs" =
class=3D"">https://www.youtube.com/watch?time_continue=3D43&amp;v=3DMjViy6=
kyiqs</a></div><div class=3D""><br class=3D""></div><div class=3D"">I =
have to say that I don=E2=80=99t really see any advantage over existing =
optical flow technology (ie twixtor). &nbsp;I did make the brave step of =
actually reading the YouTube comments, and a few people did mention =
twixtor with one person saying the nVidia version is =E2=80=9Cvastly =
superior=E2=80=9D. &nbsp;But I don=E2=80=99t see it. &nbsp;Similar =
artefacts, lots of blurring, I just don=E2=80=99t see an immediate =
advantage over existing technology. &nbsp;Of course it=E2=80=99s =
difficult to judge without access to the source footage itself. =
&nbsp;Twixtor and comparable plugins can vary widely depending on the =
quality of the source footage, with things like noise/grain and =
compression artefacts sometimes being a make or break factor. &nbsp;So =
maybe this new technology is more tolerant?</div><div class=3D""><br =
class=3D""></div><div class=3D"">What do you think?</div><div =
class=3D""><br class=3D""></div><div class=3D"">-Chris</div><div =
class=3D""><br class=3D""></div><div class=3D""><br class=3D""></div><div =
class=3D""><br class=3D""></div></body></html>=

--Apple-Mail=_3FA9B38F-0A08-44F0-8A7F-C3CE30167B8B--