journal article·2010-07

Depth‐map generation for multi‐view autostereoscopic 3‐D displays based on the SIFT algorithm constrained by boundary

Ying‐Quan Zhang, Qiong‐Hua Wang, Ai‐Hong Wang, Da‐Hai Li

Publisher page

Abstract

Abstract— A depth‐map estimation method, which converts two‐dimensional images into three‐dimensional (3‐D) images for multi‐view autostereoscopic 3‐D displays, is presented. The proposed method utilizes the Scale Invariant Feature Transform (SIFT) matching algorithm to create the sparse depth map. The image boundaries are labeled by using the Sobel operator. A dense depth map is obtained by using the Zero‐Mean Normalized Cross‐Correlation (ZNCC) propagation matching method, which is constrained by the labeled boundaries. Finally, by using depth rendering, the parallax images are generated and synthesized into a stereoscopic image for multi‐view autostereoscopic 3‐D displays. Experimental results show that this scheme achieves good performances on both parallax image generation and multi‐view autostereoscopic 3‐D displays.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Advanced Optical Imaging Technologies · Advanced Vision and Imaging · Computer Graphics and Visualization Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (16)

Show source-provided references
1. 10.1364/OL.34.00322010.1364/OL.34.003220 ↗
2. K.Dimitropouloset al. “3‐D content generation for autostereoscopic displays ”3‐DTV Conference Proc. 1–4 (2009).10.1109/3DTV.2009.5069642 ↗
3. 10.1109/TIP.2005.86033910.1109/TIP.2005.860339 ↗
4. 10.1109/MC.2005.25210.1109/MC.2005.252 ↗
5. H.Takahashiet al. “Three‐dimensional camera system for thin three‐dimensional display based on the reconstruction of parallax rays ”Second Intl. Conf. on ICIC Kumamoto 304–307 (2007).10.1109/ICICIC.2007.596 ↗
6. 10.1889/1.278551510.1889/1.2785515 ↗
7. M.F.TappenandW.T.Freeman “Comparison of graph cuts with belief propagation for stereo using identical MRF parameters ”ICCV 900–906 (2003).10.1109/ICCV.2003.1238444 ↗
8. O.P.GangwalandR.P.Berretty “Depth map post‐processing for 3‐D‐TV ”Proc. Intl. Conf. on Consumer Electronic 1–2 (2009).10.1109/ICCE.2009.5012253 ↗
9. 10.1023/B:VISI.0000029664.99615.9410.1023/B:VISI.0000029664.99615.94 ↗
10. 10.1109/TRO.2004.83922810.1109/TRO.2004.839228 ↗
11. 10.1109/FUZZY.1997.62285810.1109/FUZZY.1997.622858 ↗
12. W.H.Wang “Reach on Sobel operator for vehicle recognition ”Intl. Joint Conf. on Artificial Intelligence 448–451 (2009).10.1109/JCAI.2009.54 ↗
13. 10.1016/j.patrec.2005.03.02210.1016/j.patrec.2005.03.022 ↗
14. Y.Z.MaandW.J.Liu “Progressive matching based on segmentation for 3‐D reconstruction ”The Fifth Intl. Conf. on Computer and Information Technology Shanghai 575–579 (2005).10.1109/CIT.2005.157 ↗
15. http:vision.middlebury.edu.
16. “Capture of parallax image from 2‐D images for multi‐view autostereoscopic display