Multiple reference views for hole reduction in DIBR view synthesis

Depth-image-based rendering (DIBR) technique is widely used to synthesize virtual views in many applications including multiview and free viewpoint video systems. An inherent problem of DIBR oriented view synthesis is that holes may appear in the synthesized view. Hole filling techniques generally extrapolates/interpolates the hole regions with the neighboring information based on an assumption that the texture pattern in the hole regions is similar to that of the neighboring background information. However, in some cases especially with complex texture, the assumption may not hold. Moreover, hole filling techniques can only provide an estimation for the hole regions which may not be true. In this paper, based on a thorough examination of the hole generation mechanism in view interpolation with multiple reference views, the problem of emerging holes in a target virtual view can be greatly alleviated by making good use of other neighboring complementary views in addition to its two (commonly used) most neighboring primary views. Furthermore, a scheme of selective warping of the complementary views is developed by efficiently locating a small number of useful pixels in the complementary views for hole reduction. Experimental results show that the hole size based on two primary reference views may be reduced by about 90 percent with the help of complementary reference views, while the developed selective warping scheme can save about 69 percent of rendering time compared with fully warping two complementary reference views in the rendering process.

[1]  Béatrice Pesquet-Popescu,et al.  Depth-aided image inpainting for novel view synthesis , 2010, 2010 IEEE International Workshop on Multimedia Signal Processing.

[2]  Luc Van Gool,et al.  Advanced three-dimensional television system technologies , 2002, Proceedings. First International Symposium on 3D Data Processing Visualization and Transmission.

[3]  Dong Tian,et al.  Boundary Artifact Reduction in View Synthesis of 3D Video: From Perspective of Texture-Depth Alignment , 2011, IEEE Transactions on Broadcasting.

[4]  Liang Zhang,et al.  Virtual View Generation Based on Multiple Images , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[5]  Patrick Pérez,et al.  Region filling and object removal by exemplar-based image inpainting , 2004, IEEE Transactions on Image Processing.

[6]  Masayuki Tanimoto,et al.  3D-TV System with Depth-Image-Based Rendering , 2012 .

[7]  Lai-Man Po,et al.  A new multidirectional extrapolation hole-filling method for Depth-Image-Based Rendering , 2011, 2011 18th IEEE International Conference on Image Processing.

[8]  Guillermo Sapiro,et al.  Image inpainting , 2000, SIGGRAPH.

[9]  Luc Van Gool,et al.  ATTEST: Advanced Three-dimensional Television System Technologies , 2002 .

[10]  Yo-Sung Ho,et al.  Hole filling method using depth based in-painting for view synthesis in free viewpoint television and 3-D video , 2009, 2009 Picture Coding Symposium.

[11]  Richard Szeliski,et al.  High-quality video view interpolation using a layered representation , 2004, SIGGRAPH 2004.

[12]  Shuai Li,et al.  A New Perspective on Hole Generation and Filling in DIBR Based View Synthesis , 2013, 2013 Ninth International Conference on Intelligent Information Hiding and Multimedia Signal Processing.

[13]  Christoph Fehn,et al.  Depth-image-based rendering (DIBR), compression, and transmission for a new approach on 3D-TV , 2004, IS&T/SPIE Electronic Imaging.

[14]  Toshiaki Fujii,et al.  View Generation with 3D Warping Using Depth Information for FTV , 2008, 2008 3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video.