The following link ( describes the difference between image processing and computer graphics as being totally disconnected - image processing involves modifying a digital signal to produce one image from another, and computer graphics involves creating abstract geometric models which can be rendered as images.
Has anyone tried to combine the two approaches, and create abstract, manipulable geometric models out of existing images?

  • Isn't that what computer vision is? – Dan Hulme Aug 9 at 15:51
  • afaik, CG is more about creating images; may it be from hardware like creating images of physical 3d models using scanning techniques or may it be from software like creating an abstract data (list of vertices/points) into an image representing a shape. On the other hand Image processing is more about algorithms used to apply effects to already created images. Effects can be like noise removal, edge detection, fog removal etc. In CG we use image processing mainly for post processing I guess. – gallickgunner Aug 9 at 15:57
  • Dan Hulme - my understanding is that computer vision is about understanding scenes, and I am interested in modifying them – lightning Aug 9 at 15:59
  • Getting 3D geometry out of 2D images is usually considered part of computer vision. You may want to look into image-based rendering as more graphics-y approach. – Rahul Aug 10 at 7:39

Your Answer


By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Browse other questions tagged or ask your own question.