Jump to content
  • Advertisement
Sign in to follow this  
dodecahedron

Video - 3D Interpretation/Future of modelling

This topic is 4601 days old which is more than the 365 day threshold we allow for new replies. Please post a new topic.

If you intended to correct an error in the post then please contact us.

Recommended Posts

I just got back from seeing Chronicles of Narnia the other day, and the CGI is very good. I guess that I'm really out of touch with modeling techniques these days, but I'm wondering about something. In my experience, the way that CGI is done is that some artists use modeling tools to create the 3D models which lead eventually to a finished piece of video. My question is how much success have people had in going backwards through this process--start with a video and turn it into a 3D model? It seems like if your brain can do it to some extent, then a computer can be told how to do it. Chris Arthur

Share this post


Link to post
Share on other sites
Advertisement
This is a fairly major research area in Computer Science, and is known as Computer Vision. As you might expect, humans are still far better at this.

In some cases it is easily possible to generate a 3d model from a 2d photo (e.g using shape-from-shading), but that's generating a 3d model of the visible parts of whatever's in the photo. Us humans are pretty good at visualising parts of an object that we can't see. For a computer to do that, it needs to be able to match the 3d model to some model it has seen before and knows.

Share this post


Link to post
Share on other sites
Sign in to follow this  

  • Advertisement
×

Important Information

By using GameDev.net, you agree to our community Guidelines, Terms of Use, and Privacy Policy.

We are the game development community.

Whether you are an indie, hobbyist, AAA developer, or just trying to learn, GameDev.net is the place for you to learn, share, and connect with the games industry. Learn more About Us or sign up!

Sign me up!