Skip to main content
×
×
Home

Free-viewpoint image synthesis using superpixel segmentation

  • Mehrdad Panahpour Tehrani (a1), Tomoyuki Tezuka (a2), Kazuyoshi Suzuki (a1), Keita Takahashi (a1) and Toshiaki Fujii (a1)...
Abstract

A free-viewpoint image can be synthesized using color and depth maps of reference viewpoints, via depth-image-based rendering (DIBR). In this process, three-dimensional (3D) warping is generally used. A 3D warped image consists of disocclusion holes with missing pixels that correspond to occluded regions in the reference images, and non-disocclusion holes due to limited sampling density of the reference images. The non-disocclusion holes are those among scattered pixels of a same region or object. These holes are larger when the reference viewpoints and the free viewpoint images have a larger physical distance. Filling these holes has a crucial impact on the quality of free-viewpoint image. In this paper, we focus on free-viewpoint image synthesis that is precisely capable of filling the non-disocclusion holes caused by limited sampling density, using superpixel segmentation. In this approach, we proposed two criteria for segmenting depth and color data of each reference viewpoint. By these criteria, we can detect which neighboring pixels should be connected or kept isolated in each references image, before being warped. Polygons enclosed by the connected pixels, i.e. superpixel, are inpainted by k-means interpolation. Our superpixel approach has a high accuracy since we use both color and depth data to detect superpixels at the location of the reference viewpoint. Therefore, once a reference image that consists of superpixels is 3D warped to a virtual viewpoint, the non-disocclusion holes are significantly reduced. Experimental results verify the advantage of our approach and demonstrate high quality of synthesized image when the virtual viewpoint is physically far from the reference viewpoints.

  • View HTML
    • Send article to Kindle

      To send this article to your Kindle, first ensure no-reply@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about sending to your Kindle. Find out more about sending to your Kindle.

      Note you can select to send to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be sent to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

      Find out more about the Kindle Personal Document Service.

      Free-viewpoint image synthesis using superpixel segmentation
      Available formats
      ×
      Send article to Dropbox

      To send this article to your Dropbox account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your Dropbox account. Find out more about sending content to Dropbox.

      Free-viewpoint image synthesis using superpixel segmentation
      Available formats
      ×
      Send article to Google Drive

      To send this article to your Google Drive account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your Google Drive account. Find out more about sending content to Google Drive.

      Free-viewpoint image synthesis using superpixel segmentation
      Available formats
      ×
Copyright
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
Corresponding author
Corresponding author: M. Panahpour Tehrani Email: panahpour@nuee.nagoya-u.ac.jp
References
Hide All
[1] Tanimoto M.: Overview of free viewpoint television. Signal Process.: Image Commun., 21 (2006), 454461.
[2] Tanimoto M.; Panahpour Tehrani M.; Fujii T.; Yendo T.: Free-viewpoint TV. IEEE Signal Process. Mag., 28 (1) (2011), 6776 (invited).
[3] Tanimoto M.; Panahpour Tehrani M.; Fujii T.; Yendo T.: FTV for 3D spatial communications. Proc. IEEE, 100 (4) (2012), 905917.
[4] Matusik W.; Pfister H.: 3D TV: a scalable system for real-time acquisition, transmission and autostereoscopic display of dynamic scenes. ACM SIGGRAPH, 23 (3) (2004), 814824.
[5] Smolic A. et al. : Three-dimensional video postproduction and processing. Proc. IEEE, 99 (4) (2011), 607625.
[6] Fehn C.: Depth-image-based rendering (DIBR), compression and trans- mission for a new approach on 3DTV. SPIE USA, 5291 (2004), 93104.
[7] Mori Y.; Fukushima N.; Yendo T.; Fujii T.; Tanimoto M.: View generation with 3D warping using depth information for FTV. Signal Process.: Image Commun., 24 (2009), 6572.
[8] Yang L.; Panahpour Tehrani M.; Fujii T.; Tanimoto M.: High-quality virtual view synthesis in 3DTV and FTV. 3D Res., 2 (4) (2011), 113.
[9]ISO/IEC JTC1/SC29/WG11: View synthesis algorithm in View Synthesis Reference Software 2.0 (VSRS2.0), in MPEG Doc. M16090, Lausanne, 2009, 15.
[10] Mark W.; Mcmillan L.; Bishop G.: Post-rendering 3D warping, in Proc. Symp. I3D Graphics, 1997, 716.
[11] Daribo I.; Pesquet-Popescu B.: Depth-aided image inpainting for novel view synthesis, in IEEE Int. Workshop on Multimedia and Signal Processing, Saint-Malo, France, October 2010, 167170.
[12] Ahn I.; Kim C.: Depth-based disocclusion filling for virtual view synthesis, in IEEE Int. Conf. on Multimedia and Expo, Melbourne, Australia, July 2012, 109114.
[13] Reel S.; Cheung G.; Wong P.; Dooley L.S.: Joint texture-depth pixel inpainting of disocclusion holes in virtual view synthesis, in APSIPA ASC, Kaohsiung, Taiwan, October 2013, 17.
[14] Po L.M.; Zhang S.; Xu X.; Zhu Y.: A new multidirectional extrapolation hole-filling method for Depth-Image-Based Rendering, in 2011 18th IEEE Int. Conf. on Image Processing, Brussels, 2011, 25892592.
[15] Reel S.; Wong P.; Cheung G.; Dooley L.S.: Disocclusion Hole-Filling in DIBR-Synthesized Images using Multi-Scale Template Matching in IEEE Visual Communications and Image Processing (VCIP), Valletta, Malta, December, 2014, 494497.
[16] Mao Y.; Cheung G.; Ortega A.; Ji Y.: Expansion Hole Filling in Depth-Image-Based Rendering using Graph-based Interpolation, in IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Vancouver, Canada, May 2013, 18591863.
[17] Mao Y.; Cheung G.; Ji Y.: Image Interpolation During DIBR View Synthesis Using Graph Fourier Transform, in 3DTV-Conf. 2014, Budapest, Hungary, July 2014, 14.
[18] Shen G.; Kim W.-S.; Narang S.K.; Ortega A.; Lee J.; Wey H.: Edge-adaptive transforms for efficient depth map coding, in IEEE Picture Coding Symp., Nagoya, Japan, December 2010, 566569.
[19] Mao Y.; Cheung G.; Ji Y.: On constructing z-dimensional DIBR-synthesized images. IEEE Trans. Multimedia, 18 (8) (2016), 14531468.
[20] Zhang L.; Tam W.J.: Stereoscopic image generation based on depth images for 3D TV. IEEE Trans. Broadcasting, 51 (2005), 191199.
[21] Chen W.Y.; Chang Y.L.; Lon S.F.; Ding L.F.; Chen L.G.: Efficient depth image based rendering with edge dependent depth filter and interpolation, in Proc. of IEEE Int. Conf. on Multimedia and Expo, 2005, 13141317.
[22] Park Y.K. et al. : Depth-image-based rendering for 3DTV service over T-DMB. Signal Process.: Image Commun., 24 (2009), 122136.
[23] Horng Y.; Tseng Y.; Chang T.: Stereoscopic images generation with directional Gaussian filter, in Proc. of ISCAS, 2010, 26502653.
[24] Lee P.: Nongeometric distortion smoothing approach for depth map preprocessing. IEEE Trans. Multimedia, 13 (2) (2011), 246254.
[25] Min D.; Kim D.; Yun S.; Sohn K.: 2D/3D freeview video generation for 3DTV system. Signal Process.: Image Commun., 24 (1–2) (2009), 3148.
[26] Tian D.; Lai P.; Lopez P.; Gomila C.: View synthesis techniques for 3D video, in SPIE, Applications of Digital Image Processing XXXII, vol. 7443, 2009, 111.
[27] Radhakrishna A.: SLIC superpixels compared to state-of-the-art super- pixel methods. IEEE Trans. Pattern Analysis Machine Intelligence, 34 (2012), 22742282.
[28] Tezuka T.; Takahashi K.; Fujii T.: 3D visualization from view plus depth data using superpixel representations, in Int. Workshop on Smart Info-Media Systems in Asia, 2013, 198200.
[29] Tezuka T.; Panahpour Tehrani M.; Suzuki K.; Takahashi K.; Fujii T.: View synthesis using superpixel based inpainting capable of occlusion handling and hole filling, in Picture Coding Symp. (PCS), 2015, 124128.
[30] Chaurasia G.; Duchene S.; Sorkine-Hornung O.; Drettakis G.: Depth synthesis and local warps for plausible image-based navigation. ACM Trans. Graph., 32 (3) (2013), 30.
[31] Buyssens P.; Daisy M.; Tschumperlé D.; Lézoray O.: Superpixel-based depth map inpainting for RGB-D view synthesis, in Image Processing (ICIP), 2015 IEEE Int. Conf. on, Quebec City, QC, 2015, 43324336.
[32] Schmeing M.; Jiang X.: Faithful disocclusion filling in depth image based rendering using superpixel-based inpainting. IEEE Trans. Multimedia, 17 (12) (2015), 21602173.
[33] Lee C.; Ho Y.S.: Boundary filtering on synthesized views of 3D video, in Int. Conf. on Future Generation Communication and Networking Symposia, 2008, 1518.
[34] Daribo I.; Pesquet-Popescu B.: Depth-aided image inpainting for novel view synthesis, in IEEE International Workshop on Multimedia and Signal Processing, Saint-Malo, France, October 2010, 167170.
[35] Telea A.: An image inpainting technique based on the fast marching method, in Jr. Graphics Tools, G3-4, 2014, 2536.
[37] Zitnick L.; Kang S.B.; Uyttendaele M.; Winder S.; Szeliski R.: High- quality video view interpolation using a layered representation, in ACM SIGGRAPH and ACM Trans. on Graphics, CA, 2004, 600608.
[38]ISO/IEC JTC1/SC29/WG11: Depth estimation reference software (DERS) 4.0, in MPEG Doc M16605, June 2009, 13.
[39] Szeliski R. et al. : A comparative study of energy minimization methods for Markov random fields with smoothness-based priors. PAMI, 30 (6) (2008), 10681080.
[40] Boykov Y.; Veksler O.; Zabih R.: Fast approximate energy minimization via graph cuts, in PAMI, November 2001, 12221239.
Recommend this journal

Email your librarian or administrator to recommend adding this journal to your organisation's collection.

APSIPA Transactions on Signal and Information Processing
  • ISSN: 2048-7703
  • EISSN: 2048-7703
  • URL: /core/journals/apsipa-transactions-on-signal-and-information-processing
Please enter your name
Please enter a valid email address
Who would you like to send this to? *
×

Keywords:

Type Description Title
VIDEO
Supplementary materials

Tehrani supplementary materials S3
Supplementary Video

 Video (31.0 MB)
31.0 MB
VIDEO
Supplementary materials

Tehrani supplementary materials S1
Supplementary Video

 Video (27.4 MB)
27.4 MB
VIDEO
Supplementary materials

Tehrani supplementary materials S2
Supplementary Video

 Video (26.9 MB)
26.9 MB

Metrics

Full text views

Total number of HTML views: 73
Total number of PDF views: 164 *
Loading metrics...

Abstract views

Total abstract views: 260 *
Loading metrics...

* Views captured on Cambridge Core between 13th June 2017 - 23rd January 2018. This data will be updated every 24 hours.