Re: Finding the best pose to re-enter animation graph from ragdoll

Chris Green <[email protected]> Wed, 19 Dec 2012 19:53:58 +0000
Newsgroups gmane.games.devel.algorithms
Message-ID <E38D1C1385D38045A01B28E88043427E02D53C@exchange10.valvesoftware.com>
--===============8364582478333836191==
Content-Language: en-US
Content-Type: multipart/alternative;
	boundary="_000_E38D1C1385D38045A01B28E88043427E02D53Cexchange10valveso_"

--_000_E38D1C1385D38045A01B28E88043427E02D53Cexchange10valveso_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

I'd think you'd want to compare not just the static configuration of the po=
se but also the point/joint velocities. Your ideal choice will be one where=
 not only the pose matches well, but the body parts are also moving at simi=
lar directions and speeds to the ragdoll's current state.

From: Ben Sunshine-Hill [mailto:[email protected]]
Sent: Friday, December 14, 2012 2:35 AM
To: Game Development Algorithms
Subject: Re: [Algorithms] Finding the best pose to re-enter animation graph=
 from ragdoll

Ironically, that paper actually compares joint orientations instead of poin=
t clouds. For point cloud-based pose similarity estimation, Kovar's origina=
l motion graph paper is probably a good reference.

http://pages.cs.wisc.edu/~kovar/mographs.pdf

Ben

On Thu, Dec 13, 2012 at 9:12 PM, Michael De Ruyter <michael.deruyter@gmail.=
com<mailto:[email protected]>> wrote:
Also with the triangle normal idea, a notion of distance is missing,
so you should add something like distance hips - hand, hips - foot,
foot - foot, etc to your comparison algorithm if u were to try this
method.

Though since there is already a paper on the point cloud approach,
it's probably safer to start with it.

Sent from my iPhone

On 2012-12-13, at 12:47 PM, Richard Fine <[email protected]<mailto:rfine@tbrf.=
net>> wrote:

> On 12/13/2012 8:09 PM, Michael De Ruyter wrote:
>
>> - when comparing local quaternions for the joints, the comparison will t=
ake into
>> account the twist around the limbs even though any amount of twist doesn=
't
>> change the position of the limb. Therefore you could get drastic differe=
nces
>> when visually there are barely any.
>
> True in the general case, but I'm using a hierarchical setup, so a twist
> in an upper arm can drastically change the position/orientation of a
> forearm and so on. It matters less and less as you approach the leaf
> nodes, but this is something I intended to eliminate with weighting.
>
>> - even if the joint orientation are different the position of the limbs,
>> especially their endings like hands of feet, could still be in very clos=
e
>> positions, i.e. potentially closer than limbs with similar rotations but=
 with
>> their root joint (shoulder for instance) off by a bit.  You mention weig=
hting
>> system, but that is going to be a pain to tune.
>
> Ah, yes, OK. I'd assumed that a pose with leaf-node discrepancies would
> be less visually different than one with trunk-node discrepancies, but
> that's not a sound assumption.
>
> This sounds like it would be a problem for *any* hierarchy-based
> approach, so anything based on comparing local-space positions is
> probably a non-starter.
>
>> An other approach would be to find a comparison algorithm that compares =
the
>> overall position of the limbs.
>>
>> For instance you could consider;
>> - modeling triangles based of significant body joints, for instance
>>      + hips, shoulder, hand
>>      + hips, hand, foot
>>      + hips, shoulder, shoulder
>>
>> Then use the normal of those triangles for your pose comparison.
>>
>> You would still need to make the normals relative to the hips and then u=
se a
>> hips orientation comparison process.
>
> Right OK. Sounds similar to the point cloud approach, maybe a little
> less prone to small discrepancies, as using the normal instead of the
> joint positions would equate similar triangles.
>
> Cheers!
>
> - Richard
>
> -------------------------------------------------------------------------=
-----
> LogMeIn Rescue: Anywhere, Anytime Remote support for IT. Free Trial
> Remotely access PCs and mobile devices and provide instant support
> Improve your efficiency, and focus on delivering more value-add services
> Discover what IT Professionals Know. Rescue delivers
> http://p.sf.net/sfu/logmein_12329d2d
> _______________________________________________
> GDAlgorithms-list mailing list
> [email protected]<mailto:[email protected]=
urceforge.net>
> https://lists.sourceforge.net/lists/listinfo/gdalgorithms-list
> Archives:
> http://sourceforge.net/mailarchive/forum.php?forum_name=3Dgdalgorithms-li=
st

---------------------------------------------------------------------------=
---
LogMeIn Rescue: Anywhere, Anytime Remote support for IT. Free Trial
Remotely access PCs and mobile devices and provide instant support
Improve your efficiency, and focus on delivering more value-add services
Discover what IT Professionals Know. Rescue delivers
http://p.sf.net/sfu/logmein_12329d2d
_______________________________________________
GDAlgorithms-list mailing list
[email protected]<mailto:[email protected]=
ceforge.net>
https://lists.sourceforge.net/lists/listinfo/gdalgorithms-list
Archives:
http://sourceforge.net/mailarchive/forum.php?forum_name=3Dgdalgorithms-list


--_000_E38D1C1385D38045A01B28E88043427E02D53Cexchange10valveso_
Content-Type: text/html; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

<html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr=
osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" xmlns=3D"http:=
//www.w3.org/TR/REC-html40">
<head>
<meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Dus-ascii"=
>
<meta name=3D"Generator" content=3D"Microsoft Word 14 (filtered medium)">
<style><!--
/* Font Definitions */
@font-face
	{font-family:"Cambria Math";
	panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
	{font-family:Calibri;
	panose-1:2 15 5 2 2 2 4 3 2 4;}
@font-face
	{font-family:Tahoma;
	panose-1:2 11 6 4 3 5 4 4 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
	{margin:0in;
	margin-bottom:.0001pt;
	font-size:12.0pt;
	font-family:"Times New Roman","serif";}
a:link, span.MsoHyperlink
	{mso-style-priority:99;
	color:blue;
	text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
	{mso-style-priority:99;
	color:purple;
	text-decoration:underline;}
span.EmailStyle17
	{mso-style-type:personal-reply;
	font-family:"Calibri","sans-serif";
	color:#1F497D;}
.MsoChpDefault
	{mso-style-type:export-only;
	font-family:"Calibri","sans-serif";}
@page WordSection1
	{size:8.5in 11.0in;
	margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
	{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext=3D"edit" spidmax=3D"1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext=3D"edit">
<o:idmap v:ext=3D"edit" data=3D"1" />
</o:shapelayout></xml><![endif]-->
</head>
<body lang=3D"EN-US" link=3D"blue" vlink=3D"purple">
<div class=3D"WordSection1">
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:&quot;Ca=
libri&quot;,&quot;sans-serif&quot;;color:#1F497D">I&#8217;d think you&#8217=
;d want to compare not just the static configuration of the pose but also t=
he point/joint velocities. Your ideal choice will be one where not only
 the pose matches well, but the body parts are also moving at similar direc=
tions and speeds to the ragdoll&#8217;s current state.<o:p></o:p></span></p=
>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:&quot;Ca=
libri&quot;,&quot;sans-serif&quot;;color:#1F497D"><o:p>&nbsp;</o:p></span><=
/p>
<p class=3D"MsoNormal"><b><span style=3D"font-size:10.0pt;font-family:&quot=
;Tahoma&quot;,&quot;sans-serif&quot;">From:</span></b><span style=3D"font-s=
ize:10.0pt;font-family:&quot;Tahoma&quot;,&quot;sans-serif&quot;"> Ben Suns=
hine-Hill [mailto:[email protected]]
<br>
<b>Sent:</b> Friday, December 14, 2012 2:35 AM<br>
<b>To:</b> Game Development Algorithms<br>
<b>Subject:</b> Re: [Algorithms] Finding the best pose to re-enter animatio=
n graph from ragdoll<o:p></o:p></span></p>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
<p class=3D"MsoNormal">Ironically, that paper actually compares joint orien=
tations instead of point clouds. For point cloud-based pose similarity esti=
mation, Kovar's original motion graph paper is probably a good reference.<o=
:p></o:p></p>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><a href=3D"http://pages.cs.wisc.edu/~kovar/mographs.=
pdf">http://pages.cs.wisc.edu/~kovar/mographs.pdf</a><br>
<br>
Ben<o:p></o:p></p>
</div>
<div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
<div>
<div>
<p class=3D"MsoNormal">On Thu, Dec 13, 2012 at 9:12 PM, Michael De Ruyter &=
lt;<a href=3D"mailto:[email protected]" target=3D"_blank">michael.=
[email protected]</a>&gt; wrote:<o:p></o:p></p>
<p class=3D"MsoNormal">Also with the triangle normal idea, a notion of dist=
ance is missing,<br>
so you should add something like distance hips - hand, hips - foot,<br>
foot - foot, etc to your comparison algorithm if u were to try this<br>
method.<br>
<br>
Though since there is already a paper on the point cloud approach,<br>
it's probably safer to start with it.<br>
<br>
Sent from my iPhone<o:p></o:p></p>
<div>
<div>
<p class=3D"MsoNormal"><br>
On 2012-12-13, at 12:47 PM, Richard Fine &lt;<a href=3D"mailto:[email protected]=
et">[email protected]</a>&gt; wrote:<br>
<br>
&gt; On 12/13/2012 8:09 PM, Michael De Ruyter wrote:<br>
&gt;<br>
&gt;&gt; - when comparing local quaternions for the joints, the comparison =
will take into<br>
&gt;&gt; account the twist around the limbs even though any amount of twist=
 doesn't<br>
&gt;&gt; change the position of the limb. Therefore you could get drastic d=
ifferences<br>
&gt;&gt; when visually there are barely any.<br>
&gt;<br>
&gt; True in the general case, but I'm using a hierarchical setup, so a twi=
st<br>
&gt; in an upper arm can drastically change the position/orientation of a<b=
r>
&gt; forearm and so on. It matters less and less as you approach the leaf<b=
r>
&gt; nodes, but this is something I intended to eliminate with weighting.<b=
r>
&gt;<br>
&gt;&gt; - even if the joint orientation are different the position of the =
limbs,<br>
&gt;&gt; especially their endings like hands of feet, could still be in ver=
y close<br>
&gt;&gt; positions, i.e. potentially closer than limbs with similar rotatio=
ns but with<br>
&gt;&gt; their root joint (shoulder for instance) off by a bit. &nbsp;You m=
ention weighting<br>
&gt;&gt; system, but that is going to be a pain to tune.<br>
&gt;<br>
&gt; Ah, yes, OK. I'd assumed that a pose with leaf-node discrepancies woul=
d<br>
&gt; be less visually different than one with trunk-node discrepancies, but=
<br>
&gt; that's not a sound assumption.<br>
&gt;<br>
&gt; This sounds like it would be a problem for *any* hierarchy-based<br>
&gt; approach, so anything based on comparing local-space positions is<br>
&gt; probably a non-starter.<br>
&gt;<br>
&gt;&gt; An other approach would be to find a comparison algorithm that com=
pares the<br>
&gt;&gt; overall position of the limbs.<br>
&gt;&gt;<br>
&gt;&gt; For instance you could consider;<br>
&gt;&gt; - modeling triangles based of significant body joints, for instanc=
e<br>
&gt;&gt; &nbsp; &nbsp; &nbsp;&#43; hips, shoulder, hand<br>
&gt;&gt; &nbsp; &nbsp; &nbsp;&#43; hips, hand, foot<br>
&gt;&gt; &nbsp; &nbsp; &nbsp;&#43; hips, shoulder, shoulder<br>
&gt;&gt;<br>
&gt;&gt; Then use the normal of those triangles for your pose comparison.<b=
r>
&gt;&gt;<br>
&gt;&gt; You would still need to make the normals relative to the hips and =
then use a<br>
&gt;&gt; hips orientation comparison process.<br>
&gt;<br>
&gt; Right OK. Sounds similar to the point cloud approach, maybe a little<b=
r>
&gt; less prone to small discrepancies, as using the normal instead of the<=
br>
&gt; joint positions would equate similar triangles.<br>
&gt;<br>
&gt; Cheers!<br>
&gt;<br>
&gt; - Richard<br>
&gt;<br>
&gt; ----------------------------------------------------------------------=
--------<br>
&gt; LogMeIn Rescue: Anywhere, Anytime Remote support for IT. Free Trial<br=
>
&gt; Remotely access PCs and mobile devices and provide instant support<br>
&gt; Improve your efficiency, and focus on delivering more value-add servic=
es<br>
&gt; Discover what IT Professionals Know. Rescue delivers<br>
&gt; <a href=3D"http://p.sf.net/sfu/logmein_12329d2d" target=3D"_blank">htt=
p://p.sf.net/sfu/logmein_12329d2d</a><br>
&gt; _______________________________________________<br>
&gt; GDAlgorithms-list mailing list<br>
&gt; <a href=3D"mailto:[email protected]">GDAlgorithm=
[email protected]</a><br>
&gt; <a href=3D"https://lists.sourceforge.net/lists/listinfo/gdalgorithms-l=
ist" target=3D"_blank">
https://lists.sourceforge.net/lists/listinfo/gdalgorithms-list</a><br>
&gt; Archives:<br>
&gt; <a href=3D"http://sourceforge.net/mailarchive/forum.php?forum_name=3Dg=
dalgorithms-list" target=3D"_blank">
http://sourceforge.net/mailarchive/forum.php?forum_name=3Dgdalgorithms-list=
</a><br>
<br>
---------------------------------------------------------------------------=
---<br>
LogMeIn Rescue: Anywhere, Anytime Remote support for IT. Free Trial<br>
Remotely access PCs and mobile devices and provide instant support<br>
Improve your efficiency, and focus on delivering more value-add services<br=
>
Discover what IT Professionals Know. Rescue delivers<br>
<a href=3D"http://p.sf.net/sfu/logmein_12329d2d" target=3D"_blank">http://p=
.sf.net/sfu/logmein_12329d2d</a><br>
_______________________________________________<br>
GDAlgorithms-list mailing list<br>
<a href=3D"mailto:[email protected]">GDAlgorithms-lis=
[email protected]</a><br>
<a href=3D"https://lists.sourceforge.net/lists/listinfo/gdalgorithms-list" =
target=3D"_blank">https://lists.sourceforge.net/lists/listinfo/gdalgorithms=
-list</a><br>
Archives:<br>
<a href=3D"http://sourceforge.net/mailarchive/forum.php?forum_name=3Dgdalgo=
rithms-list" target=3D"_blank">http://sourceforge.net/mailarchive/forum.php=
?forum_name=3Dgdalgorithms-list</a><o:p></o:p></p>
</div>
</div>
</div>
<p class=3D"MsoNormal"><o:p>&nbsp;</o:p></p>
</div>
</div>
</body>
</html>

--_000_E38D1C1385D38045A01B28E88043427E02D53Cexchange10valveso_--


--===============8364582478333836191==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

------------------------------------------------------------------------------
LogMeIn Rescue: Anywhere, Anytime Remote support for IT. Free Trial
Remotely access PCs and mobile devices and provide instant support
Improve your efficiency, and focus on delivering more value-add services
Discover what IT Professionals Know. Rescue delivers
http://p.sf.net/sfu/logmein_12329d2d
--===============8364582478333836191==
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
Content-Disposition: inline

_______________________________________________
GDAlgorithms-list mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/gdalgorithms-list
Archives:
http://sourceforge.net/mailarchive/forum.php?forum_name=gdalgorithms-list
--===============8364582478333836191==--