From: "David Baud" Received: from mail-it0-f53.google.com ([209.85.214.53] verified) by media-motion.tv (CommuniGate Pro SMTP 6.1.0) with ESMTPS id 6467847 for AE-List@media-motion.tv; Wed, 20 Jun 2018 20:23:33 +0200 Received: by mail-it0-f53.google.com with SMTP id 16-v6so997856itl.5 for ; Wed, 20 Jun 2018 11:31:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:mime-version:subject:date:references:to:in-reply-to:message-id; bh=lk72V54PSfSLq1PjJkpMipDzW1EQrhxxUsEOph9cUNo=; b=G7r/xdouJx0syfYV+P/ULdHvJPWjVm551aErdMobmthhiaoJr0VlLGDvraOjCe5Tbu Fdx2v0H1vIPclRTStPAUq+5bBYHGDEno70NzsQ4gYQFRdXYQhL2JXuF8ZgM4AWEWixh9 WPgU3cNMijZ7PieqHTCka6mefFjbVPSVUxHGtCpZ3enxKUWDKVs3EDniTjAWDYJdKqpY gc8cQBncjgSwC2eYb3NXJCViwwI3NZ0nec/5KavXyP1tYPcHrvkWsW20c2d9TUoT45Ft k6T1oUfJTCm+PMrHZKgWRu8Z5hQIsedanFgHv1nAJBSD+te/PTONoQUzgHonpOvzPgHv q1jg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:mime-version:subject:date:references:to :in-reply-to:message-id; bh=lk72V54PSfSLq1PjJkpMipDzW1EQrhxxUsEOph9cUNo=; b=nAJZtyWK7H6sQtr2Kqe0IgrruazOBBS6c1/xY9pWlyrvSh0geIfdLAK1kIjwa6TwGy 1QO4YEcG9kVeGdSv3WAlE11pxaIAm0SyqYeeeN8wBzFc37Y6hwmSibzLhUuJOvemomXb goPJdwz7OU9BBd7bcR+p+5Wf7g8FKewnTueYbJnjs0r0v21r4bqo9A2P1PZiLren6vbZ K088y4dtkUsftDtvqOpa5AxhREUi8NdUmkuBsZ3D5mFKVKNhPFbYiV9jb92e5HUrI5gT Jkk55PySSxF9BRpCU1FThInmwoy/a/aNNmbePRcrncG9/7/T9640b5UKB26/jIEN/uEG BNTQ== X-Gm-Message-State: APt69E05wl7g8Pm3WXAHFmQ7s842krjx8Ypw0XS7onTHnWhWvVAigkYz +f1xyF8SztphD1IBauVZIPnjEV6n X-Google-Smtp-Source: ADUXVKLtTd6F0zUbbdKSzN+kZmKOQK+W+PmZKxyN5mQ4fBHU84E/nVuSBJH1jCbclDtmanhxqT1reg== X-Received: by 2002:a02:4fc7:: with SMTP id r68-v6mr18148003jad.21.1529519476164; Wed, 20 Jun 2018 11:31:16 -0700 (PDT) Return-Path: Received: from ?IPv6:2601:285:102:4d18:ca2:cdc0:3e3c:1b11? ([2601:285:102:4d18:ca2:cdc0:3e3c:1b11]) by smtp.gmail.com with ESMTPSA id k139-v6sm1632315itk.27.2018.06.20.11.31.14 for (version=TLS1_2 cipher=ECDHE-RSA-AES128-GCM-SHA256 bits=128/128); Wed, 20 Jun 2018 11:31:15 -0700 (PDT) Content-Type: multipart/alternative; boundary="Apple-Mail=_BB16DFE0-A0C0-4B9F-9C04-B88E086FC7DB" Mime-Version: 1.0 (Mac OS X Mail 10.3 \(3273\)) Subject: Re: [AE] nVidias Slo mo demo Date: Wed, 20 Jun 2018 12:31:14 -0600 References: To: After Effects Mail List In-Reply-To: Message-Id: <39126FD9-EE53-408D-BEDC-D85F71DE496D@gmail.com> X-Mailer: Apple Mail (2.3273) --Apple-Mail=_BB16DFE0-A0C0-4B9F-9C04-B88E086FC7DB Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=utf-8 My understanding is that in order to get good result with any of the = optical flow solutions, the system needs to be able to define the = contour of your moving =E2=80=9Cobjects=E2=80=9D (i.e a person, a ball, = a car, etc=E2=80=A6) in your frame. Better the system is capable of = recognizing these objects, better results you will get. Twixtor Pro = version will let you =E2=80=9Chelp=E2=80=9D the system to define these = contour by providing a mask for your object. As we know it can be time = consuming to do rotoscoping. Where I think these systems can improve is = in the automatic recognition of the moving objects in your frame, i.e = recognizing "the person walking" and "the picket fence" as two different = objects. I am not familiar with the proposed technology by nVidia, but = maybe they improved the analysis of a video and the system is capable of = calculating automatically the displacement of all objects in a frame = separately? Maybe Peter with RE:Vision will chime in this discussion and correct me = if I am wrong =F0=9F=98=89=E2=80=A6 and maybe gives us a better = understanding of the optical flow technology in general=E2=80=A6 without = revealing his secret sauce for Twixtor! David Baud Colorist & Finishing Editor david at kosmos-productions.com > On Jun 20, 2018, at 11:59 , Jim Curtis = wrote: >=20 > Optical Flow and Twixtor have limitations. Try a slo-mo of a person = walking next to a picket fence, and see how wacky the pickets become = with any method besides frame-blending. There have been occasions where = I=E2=80=99ve stitched together the different methods with masking and = editing, as there seems not to be a Silver Bullet so far. If this is = it, I=E2=80=99m interested! Thanks for the head=E2=80=99s up. --Apple-Mail=_BB16DFE0-A0C0-4B9F-9C04-B88E086FC7DB Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset=utf-8 My understanding is that in order to get good result with any = of the optical flow solutions, the system needs to be able to define the = contour of your moving =E2=80=9Cobjects=E2=80=9D (i.e a person, a ball, = a car, etc=E2=80=A6) in your frame. Better the system is capable of = recognizing these objects, better results you will get. Twixtor Pro = version will let you =E2=80=9Chelp=E2=80=9D the system to define these = contour by providing a mask for your object. As we know it can be time = consuming to do rotoscoping. Where I think these systems can improve is = in the automatic recognition of the moving objects in your frame, i.e = recognizing "the person walking" and "the picket fence" as two different = objects. I am not familiar with the proposed technology by nVidia, but = maybe they improved the analysis of a video and the system is capable of = calculating automatically the displacement of all objects in a frame = separately?

Maybe = Peter with RE:Vision will chime in this discussion and correct me if I = am wrong =F0=9F=98=89=E2=80=A6 and maybe gives us a better understanding = of the optical flow technology in general=E2=80=A6 without revealing his = secret sauce for Twixtor!

David Baud
Colorist & Finishing = Editor
david = at kosmos-productions.com

On Jun 20, 2018, at 11:59 , Jim Curtis <AE-List@media-motion.tv> wrote:

Optical Flow = and Twixtor have limitations.  Try a slo-mo of a person walking = next to a picket fence, and see how wacky the pickets become with any = method besides frame-blending.  There have been occasions where = I=E2=80=99ve stitched together the different methods with masking and = editing, as there seems not to be a Silver Bullet so far.  If this = is it, I=E2=80=99m interested!  Thanks for the head=E2=80=99s = up.

= --Apple-Mail=_BB16DFE0-A0C0-4B9F-9C04-B88E086FC7DB--