The Next Big Innovations in CG ? 2012 - 2015

Become a member of the CGSociety

Connect, Share, and Learn with our Large Growing CG Art Community. It's Free!

Thread Tools Display Modes
  01 January 2012
The Next Big Innovations in CG ? 2012 - 2015

Hello all,

I thought it would be interesting to discuss what people think will be, or could be, the NEXT big innovations in CG, coming in the next 3 years or so (or at least doable with current technologgy in the next 3 years).

I'll post the first suggestion:

Photorealism Assistance Algorithm/Intelligent Re-Shading and Shading Transfer Algorithm

1) Analyzes the shading of a rendered image.
2) Intelligently alters the shading of that image (using statistical methods or similar) to create a much more Photoreal looking result
3) You can also provide a photograph or other image whose look/shading you want to mimick, and the PAA will automagically apply/transfer that type of shading (or "shading profile") onto your rendered image.

That's my suggestion for the Next Big Innovation.

I am curious to hear other people's suggestions now.
  01 January 2012
real time stereo conversion!

  01 January 2012
Originally Posted by tommy138: real time stereo conversion!

From what I've heard talking to some people who seemed to be in the know, a lot of PhD students in computing science/image processing/computer graphics are, apparently, currently working on the 2D-to-Stereo3D problem. Its particularly popular in universities in Asia/China, I've been told.

So no worries there. Somebody somewhere is going to solve this problem properly in the next 3 years or so.
  01 January 2012
Not this thread again!

Search function is your friend.

[tommy138 - seriously lol'd]

  01 January 2012
I've struggled with 3D on and off. Sometimes I just get frustrated and stop then go back months or years later and I am able to do what set me back years ago with absolutely no problem. I think hidden barriers of how to do things will be simplified. I swear to god if you know a few key elements all of a sudden everything is easy but then you just need the motivation and the creativity to put in the effort. I look forward to seeing little kids doing what I could never do.
  01 January 2012
an algorithm that does everything for me
  01 January 2012
Hopefully soon:
Software that rearranges oxygen on the sub atomic level
to produce ,for me, an unlimited supply of jelly doughnuts!

  01 January 2012
I'd just be happy with software that's more stable and better supported. Hopefully with less draconian licensing.
  01 January 2012
the next step, i think would still be focused on rendering. GPU renders are on the horizon. Once you can render out frames with the fluidity of playing video games. The CG industry will change... ALOT.. Less overhead for smaller shops and perhaps even individuals can start outputting amazing cg shorts....
  01 January 2012
Originally Posted by cooperunionstud: the next step, i think would still be focused on rendering. GPU renders are on the horizon.

If your browser supports WebGL, there's a very cool, and surprisingly fast interactive demo of GPU accelerated RayTracing/PathTracing at this URL:

You can change the camera viewpoint by click-dragging the mouse, and move objects around the 3D scene by left-click selecting them, and dragging them around.
  01 January 2012
Originally Posted by CHRiTTeR: an algorithm that does everything for me

Here's an Al Gore Rhythm for you.

  01 January 2012
I want my software to do all my work for me, so I can spend more time playing my banjo.
  01 January 2012
Originally Posted by Artbot: Here's an Al Gore Rhythm for you.

Where's a Like button when you need one?!
  01 January 2012
I see the most progress happening in the realm of "reality capture".

More advanced and higher detailed lidar scanning
123D Catch
Better and Faster HDR capture
HDR Video
More motion control rigs.
Better Motion Capture.
Better Pointcloud and Depth Capture
Material property scanning.

Also quite a lot of progress with "brute force" kind of renderers like Arnold, Vray and Maxwell. Not that the tech is so new, but the computer power can actually do it now. Maxwell can still take 48 hours to render a HD1080 frame, but that's better than a week

I foresee a massive amount of data being captured and analyzed on shoots, then having the the basics of a scene ready to go semi-automatically. So integration and rendering and lighting will be much more physically accurate and automated.

Beyond that, it's a safe bet that many things that are computationally heavy will get much faster and more refined. The math behind fluid dynamics is much farther ahead of what are current processing power can handle, alot of that stuff was farther ahead in the 50's, but now we can actually see if it really works

that's my prediction at least.

Chris Smallfield
Freelance VFX Supervisor / Artist, Berlin
  01 January 2012
I expect mocap to become mainstream (kinect 2) and realtime tesselation to take off with new consoles (dx11/ogl4). Plus 3d printers will hopefullly become cheaper.
"Any intelligent fool can make things bigger, more complex & more violent..." Einstein
Thread Closed share thread

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

vB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Society of Digital Artists

Powered by vBulletin
Copyright 2000 - 2006,
Jelsoft Enterprises Ltd.
Minimize Ads
Forum Jump

All times are GMT. The time now is 08:02 AM.

Powered by vBulletin
Copyright ©2000 - 2018, Jelsoft Enterprises Ltd.