3D from arbitrary 2D video

Ianir A. Ideses*, Leonid P. Yaroslavsky

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


In this paper, we present methods to synthesize 3D video from arbitrary 2D video. The 2D video is analyzed by computing frame-by-frame motion maps. For this computation, several methods were tested, including optical flow, segmentation and correlation based target location. Using the computed motion maps, the video undergoes analysis and the frames are segmented to provide object-wise depth ordering. The frames are then used to synthesize stereo pairs. This is performed by resampling frames on a grid that is governed by a corresponding depth-map. In order to improve the quality of the synthetic video, as well as to enable 2D viewing where 3D visualization is not possible, several techniques for image enhancement are used. In our test case, anaglyph projection was selected as the 3D visualization method, as the method is mostly suited to standard displays. The drawback of this method is ghosting artifacts. In our implementation we minimize these unwanted artifacts by modifying the computed depth-maps using non-linear transformations. Defocusing of one anaglyph color component was also used to counter such artifacts. Our results show that the suggested methods enable synthesis of high quality 3D videos.

Original languageEnglish
Title of host publicationThree-Dimensional Image Capture and Applications VII - Proceedings of SPIE-IS and T Electronic Imaging
StatePublished - 2006
EventThree-Dimensional Image Capture and Applications VII - San Jose, CA, United States
Duration: 16 Jan 200617 Jan 2006

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X


ConferenceThree-Dimensional Image Capture and Applications VII
Country/TerritoryUnited States
CitySan Jose, CA


  • 3D
  • Anaglyph
  • Artificial-Stereo
  • Depth-Maps


Dive into the research topics of '3D from arbitrary 2D video'. Together they form a unique fingerprint.

Cite this