Comments on: Contour: A Novel Technique for Modeling and Capture http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/ A group blog about computer narrative, games, poetry, and art. Wed, 19 May 2010 01:52:58 -0700 http://wordpress.org/?v=2.8.5 hourly 1 By: christalnightshade http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/comment-page-1/#comment-117690 christalnightshade Fri, 08 Jun 2007 19:05:36 +0000 http://grandtextauto.org/?p=1251#comment-117690 Hey not a bad blog... anyway just checking in and seeing that this is about photography and 3D and I see that there is not much to say in the matter here because I don't know what something valley is for. Though it is easy to change the pixels of a photograph when you have the right scanner or by the use of a friends or a shops... hehe anyway continue. Hey not a bad blog… anyway just checking in and seeing that this is about photography and 3D and I see that there is not much to say in the matter here because I don’t know what something valley is for. Though it is easy to change the pixels of a photograph when you have the right scanner or by the use of a friends or a shops… hehe anyway continue.

]]> By: randform » Blog Archive » the uncanny valley http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/comment-page-1/#comment-117454 randform » Blog Archive » the uncanny valley Sun, 03 Jun 2007 11:42:56 +0000 http://grandtextauto.org/?p=1251#comment-117454 [...] chologist Prof. Siegfried Frey in his talk on the NMI conference. I read about it first on grandtextauto blog po [...] [...] chologist Prof. Siegfried Frey in his talk on the NMI conference. I read about it first on grandtextauto blog

po [...]

]]> By: andrew http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/comment-page-1/#comment-91208 andrew Sat, 05 Aug 2006 04:31:20 +0000 http://grandtextauto.org/?p=1251#comment-91208 We've discussed the uncanny valley <a href="http://www.google.com/search?as_q=uncanny+valley&num=50&hl=en&newwindow=1&btnG=Google+Search&as_epq=&as_oq=&as_eq=&lr=&as_ft=i&as_filetype=&as_qdr=all&as_nlo=&as_nhi=&as_occt=any&as_dt=i&as_sitesearch=grandtextauto.org" rel="nofollow">many times</a> on GTxA; it's definitely an issue, and I'm excited to see Contour making progress towards crossing it, for non-procedural animation anyway. We’ve discussed the uncanny valley many times on GTxA; it’s definitely an issue, and I’m excited to see Contour making progress towards crossing it, for non-procedural animation anyway.

]]> By: Steve Perlman http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/comment-page-1/#comment-91202 Steve Perlman Sat, 05 Aug 2006 04:17:33 +0000 http://grandtextauto.org/?p=1251#comment-91202 Well, whether or not the "Uncanny Valley" is a valid theoretical construct, it is still the case that it is extremely difficult (arguably impractical) to drive a convincingly photoreal human face with a marker-based capture system. Our brains are wired from birth to notice very subtle nuances in faces, and we are much more attuned to detecting slight defects a face than we are in other parts of the body (e.g. the forearm). So, what might be a completely unnoticeable inaccuracy in modeling and animating most of the body, may stand out very noticeably in the face. Contour provides a volumetric (i.e. in voxels) capture of a face approaching the same resolution as what you capture with a conventional HD camera (i.e. in pixels) from a single viewpoint. It looks just as photoreal in 3D as it looks in 2D as captured with a conventional camera. So, whether we describe this as being "beyond the Uncanny Valley", or simply say that "the facial innacuracies are not noticeable", the end result is the same: You have a tool at your disposal to give you a starting point in 3D facial animation that is photoreal. Then, you can take it from there for whatever creative purpose suits your application. -- Steve Perlman, president, Mova Well, whether or not the “Uncanny Valley” is a valid theoretical construct, it is still the case that it is extremely difficult (arguably impractical) to drive a convincingly photoreal human face with a marker-based capture system. Our brains are wired from birth to notice very subtle nuances in faces, and we are much more attuned to detecting slight defects a face than we are in other parts of the body (e.g. the forearm). So, what might be a completely unnoticeable inaccuracy in modeling and animating most of the body, may stand out very noticeably in the face.

Contour provides a volumetric (i.e. in voxels) capture of a face approaching the same resolution as what you capture with a conventional HD camera (i.e. in pixels) from a single viewpoint. It looks just as photoreal in 3D as it looks in 2D as captured with a conventional camera. So, whether we describe this as being “beyond the Uncanny Valley”, or simply say that “the facial innacuracies are not noticeable”, the end result is the same: You have a tool at your disposal to give you a starting point in 3D facial animation that is photoreal. Then, you can take it from there for whatever creative purpose suits your application.

– Steve Perlman, president, Mova

]]> By: Louis Dargin http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/comment-page-1/#comment-91159 Louis Dargin Fri, 04 Aug 2006 20:27:52 +0000 http://grandtextauto.org/?p=1251#comment-91159 Softimage's Face|Robot product works with this. See the details <a href="http://www.softimage.com/products/face_robot/game_export/default.aspx">here</a> Softimage’s Face|Robot product works with this. See the details here

]]> By: josh g. http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/comment-page-1/#comment-91140 josh g. Fri, 04 Aug 2006 15:00:14 +0000 http://grandtextauto.org/?p=1251#comment-91140 From what I heard, the evidence was King Kong on the XBox 360. From what I heard, the evidence was King Kong on the XBox 360.

]]> By: monkeysan http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/comment-page-1/#comment-91084 monkeysan Fri, 04 Aug 2006 00:43:26 +0000 http://grandtextauto.org/?p=1251#comment-91084 This is indeed an amazing development. However, since I don't believe the uncanny valley really exists in the first place, I'm more interested in what it makes possible in media rather than whether it cuts across a theoretical construct that has never been validated with convincing evidence. This is indeed an amazing development. However, since I don’t believe the uncanny valley really exists in the first place, I’m more interested
in what it makes possible in media rather than whether it cuts across a theoretical construct that has never been validated with convincing evidence.

]]> By: andrew http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/comment-page-1/#comment-90980 andrew Wed, 02 Aug 2006 20:01:22 +0000 http://grandtextauto.org/?p=1251#comment-90980 You're right that lots of raw sample data can be of help creating a procedural model, but it's only a starting point. And you're right that nearer-term facial expression techniques will be a hybrid of keyframe and procedural. Facade's characters were. You’re right that lots of raw sample data can be of help creating a procedural model, but it’s only a starting point.

And you’re right that nearer-term facial expression techniques will be a hybrid of keyframe and procedural. Facade’s characters were.

]]> By: Breaker http://grandtextauto.org/2006/07/31/contour-a-novel-technique-for-modeling-and-capture/comment-page-1/#comment-90972 Breaker Wed, 02 Aug 2006 17:25:09 +0000 http://grandtextauto.org/?p=1251#comment-90972 I think it does help cross the uncanny valley. For non-interactive media the high resolution helps capture detailed facial features that would otherwise be unsettlingly absent, especially skin texture which is impossible to get with reflective dots. The uncanny valley exists in both interactive and non-interactive media after all. See Final Fantasy for a great example of unsettling non-interactive CG. For interactive media you have a low cost method of generating lots of expression examples to calibrate a procedural expression model. The many cases can help a computer take the raw positional information and create a dynamic skeletal, flesh, skin model without human input. That model can then be animated procedurally in ways the actor never moved or map those same movements to a different model all together. Eye positioning is really important and missing from this particular technique. I think that eyes can be tracked from raw video with relative ease these days anyhow. As a physical object, eyes are relatively similiar between people, absent a few variables like size and color. Eyelids and apparent eye shape may or may not be picked up properly by the make-up. It's hard to know where the border is. So what's left? Well the brain behind the mask. That's the tough part! Still it is quite helpful in my mind. Imagine if you could take data from feature length movies, and identify key frames of the actors and actresses expressions using key frame analysis against a generic database. Then you use those identified sequences with generic expression key frames. That would make procedurally generated faces look a lot more natural. I think it does help cross the uncanny valley. For non-interactive media the high resolution helps capture detailed facial features that would otherwise be unsettlingly absent, especially skin texture which is impossible to get with reflective dots. The uncanny valley exists in both interactive and non-interactive media after all. See Final Fantasy for a great example of unsettling non-interactive CG.

For interactive media you have a low cost method of generating lots of expression examples to calibrate a procedural expression model. The many cases can help a computer take the raw positional information and create a dynamic skeletal, flesh, skin model without human input. That model can then be animated procedurally in ways the actor never moved or map those same movements to a different model all together. Eye positioning is really important and missing from this particular technique. I think that eyes can be tracked from raw video with relative ease these days anyhow. As a physical object, eyes are relatively similiar between people, absent a few variables like size and color. Eyelids and apparent eye shape may or may not be picked up properly by the make-up. It’s hard to know where the border is.

So what’s left? Well the brain behind the mask. That’s the tough part!

Still it is quite helpful in my mind. Imagine if you could take data from feature length movies, and identify key frames of the actors and actresses expressions using key frame analysis against a generic database. Then you use those identified sequences with generic expression key frames. That would make procedurally generated faces look a lot more natural.

]]>