Abstract
In this paper, we proposed stereoscopic image generation methods of adjusting the depth value of edge pixels and improved hole filling procedures. For the conventional system, the smooth of depth map can reduce the incidence of image holes, but cause geometric distortions of the image depth. To solve the problems, the depth map is first expanded to refine the accuracy of image depth and the quality of images. Next, we derive a hardware-oriented method for 3D warping. Finally, appropriate blocks are searched to enhance the performance of image by improving hole-filling procedures. The experimental results demonstrate the proposed methods have great performance and practicability.
Similar content being viewed by others
References
Bertalmio M, Sapiro G, Caselles V, Ballester C (2000) Image inpainting. Proc 27th Ann Conf Comput Graph Interact Tech:417–424
Bosc E, Koppel M, Pepion R, Pressigout M, Morin L, Ndjiki-Nya R et al (2011) Can 3D synthesized views be reliably assessed through usual subjective and objective evaluation protocols?. 18th IEEE Int Conf Image Process (ICIP): 2597–2600
Chen H-C ()2010 Real-time stereoscopic image generation using depth image based rendering with virtual view point estimation. Master’s Thesis, Dept. of Electrical Engineering, National Cheng Kung University
Chen H-J, Lo F-H, Jan F-C, Wu S-D (2010) Real-time multiview rendering architecture for autostereoscopic displays. Proc IEEE Int Symp Circ Syst (ISCAS): 1165–1168
Criminisi A, Pérez P, Toyama K (2004) Region filling and object removal by exemplar-based image inpainting. IEEE Trans Image Process 13:1200–1212
Gortler SJ, Grzeszczuk R, Szeliski R, Cohen MF (1996) The lumigraph. Proc 23rd Ann Conf Comput Graph Interact Techn: 43–54
Jung KH, Park YK, Kim JK, Lee H, Yun K, Hur N et al. (2008) Depth image based rendering for 3D data service over T-DMB. 3DTV Conf: True Vision-Capture, Trans Display 3D Video: 237–240
Kubota A, Smolic A, Magnor M, Tanimoto M, Chen T, Zhang C (2007) Multiview imaging and 3DTV. IEEE Signal Process Mag 24(6):10–21
Mark WR (1999) Post-rendering 3D image warping: visibility, reconstruction, and performance for depth image warping. PhD thesis, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
McMillan L (1997) An image-based approach to three-dimensional computer graphics. PhD thesis, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA
Mori Y, Fukushima N, Yendo T, Fujii T, Tanimoto M (2009) View generation with 3D warping using depth information for FTV. Signal Process Image Commun 24(1–2):65–72
Muller K, Smolic A, Dix K, Merkle P, Kauff P, Wiegand T (2008) View synthesis for advanced 3D video systems. EURASIP J Image Video Process: 1–11
Ndjiki-Nya P, Koppel M, Doshkov D, Lakshman H, Merkle P, Muller K, Wiegand T (2011) “Depth image-based rendering with advanced texture synthesis for 3D video. IEEE Trans Multimed 13(3):453–465
Oliveira MM (2000) Relief texture mapping. PhD thesis, University of North Carolina
Sharma M, Chaudhury S, Lall B, Venkatesh MS (2014) A flexible architecture for multi-view 3DTV based on uncalibrated cameras. J Vis Commun Image Represent 25(4):599–621
Shum H (2000) Review of image-based rendering techniques. Proc SPIE: 2–13
Shum H, He L (1999) Rendering with concentric mosaics. Proc 26th Ann Conf Comput Graph Interact Techn: 299–306
Smolic A (2009) An overview of 3D video and free viewpoint video. Sign Process:1–8
Smolic A, Mller K, Dix K, Merkle P, Kauff P, Wiegand T (2008) Intermediate view interpolation based on multiview video plus depth for advanced 3D video systems. Image Process: 2448–2451
Solh M, AlRegib G (2012) Hierarchical hole-filling for depth-based view synthesis in FTV and 3D video. IEEE J Select Topics Sign Process 6:495–504
Sun S-P, Chou Y-J, Chiu Y-H (2010) Multimedia 3D clinical planning system for simulation of internal fixation surgery for calcaneal collapse. Multimed Tools Appl 52(1):5–18
Szeliski R, Anandan P (2000) The geometry-image representation trade-off for rendering. Proc 2000 Int Conf Image Process 2:13–16
Tam WJ, Alain G, Zhang L, Martin T, Renaud R (2004) “Smoothing depth maps for improved stereoscopic image quality. Proc SPIE Conf Three-Dimensional TV, Video, Display III 5599:162–172
Wang L, Hou C, Lei J, Yan W (2015) View generation with DIBR for 3D display system. Multimed Tools Appl 74(21):9529–9545
Wang D, Zhao Y, Zheng W, Chen H (2015) Hole-filling for DIBR based on depth and gradient information. Int J Adv Robot Syst. doi:10.5772/60060
Xu X, Po L-M, Cheung K-W, Ng K-H, Wong K-M, Ting C-W (2012) A foreground biased depth map refinement method for DIBR view Synthesis. IEEE Int Conf Acoustics, Speech Signal Process (ICASSP): 805–808
Xu Z, Sun J (2010) Image inpainting by patch propagation using patch sparsity. IEEE Trans Image Process 19:1153–1165
Yang SB, Liang TW (2012) Image restoration based on smooth gray-level detection and line prediction method for large missing regions. Int J Image Graph 12:1250013 [20 pages]
Zhang L, Tam WJ (2005) Stereoscopic image generation based on depth images for 3D TV. IEEE Trans Broadcast 51(2):1191–1199
Zinger S, Ruijters D, de With PHN (2009) iGLANCE project: free-viewpoint 3D video. 17th Int Conf Comput Graph, Visual Comput Vision (WSCG):313–319
Zitnick CL, Kang SB, Uyttendaele M, Winder S, Szeliski R (2004) High-quality video view interpolation using a layered representation. ACM Trans Graph (TOG) 23:600–608
Acknowledgments
This work was supported in part by the National Science Council, R.O.C., under Grant MOST 104-2221-E-024-001
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kao, CC. Stereoscopic image generation with depth image based rendering. Multimed Tools Appl 76, 12981–12999 (2017). https://doi.org/10.1007/s11042-016-3733-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3733-3