2D to 3D Image Conversion Based on Classification of Background Depth Profiles

  • Guo-Shiang Lin
  • Han-Wen Liu
  • Wei-Chih Chen
  • Wen-Nung Lie
  • Sheng-Yen Huang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7088)


In this paper, a 2D to 3D stereo image conversion scheme is proposed for 3D content creation. The difficulty in this problem lies on depth estimation/assignment from a mono image, which actually does not have sufficient information. To estimate the depth map, we adopt a strategy of performing foreground/background separation first, then classifying a background depth profile by neural network, estimating foreground depth from image cues, and finally combining them. To enhance stereoscopic perception for the synthesized images viewed on 3D display, depth refinement based on bilateral filter and HVS-based contrast modification between the foreground and background are adopted. Subjective experiments show that the stereo images generated by using the proposed scheme can provide good 3D perception.


2D to 3D image conversion background depth profile stereoscopic perception depth cue estimation 


  1. 1.
    Nayar, S.K., Nakagawa, Y.: Shape from Focus. IEEE Trans. on Pattern Analysis and Machine Intelligence 16(8), 824–831 (1994)CrossRefGoogle Scholar
  2. 2.
    Namboodiri, V.P., Chaudhuri, S.: Recovery of Relative Depth from a Single Observation Using an Uncalibrated (Real-Aperture) Camera. In: Proc. of IEEE International Conference on Computer Vision and Pattern Recognition, Anchorage, AK, pp. 1–6 (2008) Google Scholar
  3. 3.
    Burazerovic, D., Vandewalle, P., Berretty, R.P.: Automatic Depth Profiling of 2D Cinema - and Photographic Images. In: Proc. of IEEE International Conference on Image Processing, Cairo, pp. 2365–2368 (2009)Google Scholar
  4. 4.
    Kim, M., Park, S., Kim, H., Artem, I.: Automatic conversion of two-dimensional video into stereoscopic video. In: Proc. of SPIE, vol. 6016, pp. 601610-1–601610-8 (2005)Google Scholar
  5. 5.
    Manbae, K., Sanghoon, P., Youngran, C.: Object-Based Stereoscopic Conversion of MPEG-4 Encoded Data. In: Proc. of the 5th Pacific-Rim Conference on Multimedia, pp. 491–498 (2004)Google Scholar
  6. 6.
    Kim, D., Min, D., Sohn, K.: A Stereoscopic Video Generation Method Using Stereoscopic Display Characterization and Motion Analysis. IEEE Trans. on Broadcasting 54(2), 188–197 (2008)CrossRefGoogle Scholar
  7. 7.
    Suzuki, M.T., Yaginuma, Y., Yamada, T., Shimizu, Y.: A Shape Feature Extraction Method Based on 3D Convolution Masks. In: Proc. of Eighth IEEE International Symposium on Multimedia, pp. 837–844 (2006)Google Scholar
  8. 8.
    Peer, P., Kovace, J., Solina, F.: Human Skin Color Clustering for Face Detection. In: EU1ROCON 2003 International Conf. on Computer as a Tool, vol. 2, pp. 144–148 (2003)Google Scholar
  9. 9.
    Chen, Y.-J., Lin, Y.-C.: Simple Face-detection Algorithm Based on Minimum Facial Features. In: Proc. of IEEE International Conference on Industrial Electronics Society, pp. 455–460 (2007)Google Scholar
  10. 10.
    Sudhamani, M.V., Venugopal, C.R.: Segmentation of Color Images using Mean Shift Algorithm for Feature Extraction. In: Proc. of IEEE International Conference on Information Technology (2006)Google Scholar
  11. 11.
    Tomasi, C., Manduchi, R.: Bilateral Filtering for Gray and Color Images. In: Proc. of IEEE International Conference on Computer Vision, Bombay, pp. 839–846 (1998)Google Scholar
  12. 12.
    Lin, G.-S., Yeh, C.-Y., Chen, W.-C., Lie, W.-N.: A 2D to 3D conversion scheme based on depth cues analysis for MPEG videos. In: IEEE International Conference on Multimedia and Expo, pp. 1141–1145 (2010)Google Scholar
  13. 13.
    Han, K., Hong, K.: Geometric and texture cue based depth-map estimation for 2D to 3D image conversion. In: IEEE International Conference on Consumer Electronics, pp. 651–652 (2011)Google Scholar
  14. 14.
    Chiang, T.-W., Tsai, T., Lin, Y.-H., Hsiao, M.-J.: Fast 2D to 3D conversion based on wavelet analysis. In: IEEE International Conference on Systems Man and Cybernetics, pp. 3444–3448 (2010)Google Scholar
  15. 15.
    Liu, B., Gould, S., Koller, D.: Single image depth estimation from predicted semantic labels. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1253–1260 (2010)Google Scholar
  16. 16.
    Choi, J., Kim, W., Kong, H., Kim, C.: Real-time vanishing point detection using the local dominant orientation signature. In: 3DTV Conf., Turkey (May 2011)Google Scholar
  17. 17.
    Saxena, A., Sun, M., Ng, A.Y.: Learning 3-D Scene Structure from a Single Still Image. In: ICCV 2007 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Guo-Shiang Lin
    • 1
  • Han-Wen Liu
    • 2
  • Wei-Chih Chen
    • 2
  • Wen-Nung Lie
    • 2
  • Sheng-Yen Huang
    • 3
  1. 1.Dept. of Computer Science and Information EngineeringDa-Yeh UniversityChang-HuaR.O.C.
  2. 2.Department of Electrical EngineeringNational Chung Cheng UniversityChia-YiR.O.C.
  3. 3.Reallusion Inc.New Taipei CityTaiwan

Personalised recommendations