Abstract
In this paper, a new technique to generate high resolution depth image is proposed. First, a low resolution depth map is obtained by the time-of-flight depth camera. Then a high resolution depth map for a given view is generated by depth warping followed by depth value refinement taking into account the color information at the given view. The edge in the final depth map is then processed by bilateral filtering for edge preserving. With the color image and the corresponding depth image, novel view synthesis can be carried out by depth image based rendering (DIBR). Experimental results show that the depth map generated by the proposed technique is able to ensure novel view images with high quality.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
ISO/IEC JTC1/SC29/WG11 M8595, FTV-Free Viewpoint Television (2002)
Seiz, S.M., Dyer, C.R.: View Morphing. In: Proc. of SIGGRAPH, pp. 21–30 (1996)
Debevec, P.E., Yu, Y., Borshukov, G.: Efficient View-dependent Image-based Rendering with Projective Texture Mapping. In: Proc. of Eurographics Rendering Workshop, pp. 105–116 (1998)
Fehn, C.: A 3D-TV Approach Using Depth-Image-Based-Rendering (DIBR). In: Proc. of Visualization, Imaging, and Image Processing, pp. 482–487 (2003)
Fehn, C.: Depth-Image-Based Rendering (DIBR), Compression and Transmission for a New Approach on 3D-TV. In: SPIE-IS&T, vol. 5291, pp. 93–104 (January 2004)
Fujii, T., Kimoto, T., Tanimoto, M.: Ray Space Coding for 3D Visual Communication. In: Proc. of Picture Coding Symposium, pp. 447–451 (March 1996)
Naemura, T., Kaneko, M., Harashima, H.: 3-D Visual Data Compression Based on Ray-Space Projection. In: Proc. of SPIE VCIP, pp. 413–424 (1997)
Daribo, I., Tillier, C., Pesquet-Popescu, B.: Distance Dependent Depth Filtering in 3D Warping for 3DTV. In: Proc. of IEEE Int’l Conf. on Multimedia Signal Processing (MMSP), Chania, Crete, Greece, pp. 312–315 (October 2007)
Cheng, C.-M., Lin, S.-J., Lai, S.-H., Yang, J.-C.: Improved Novel View Synthesis from Depth Image with Large Baseline. In: Proc. of IEEE Int’l Conf. on Pattern Recognition (2008)
Mori, Y., Fukushima, N., Yendo, T., Fujii, T., Tanimoto, M.: View Generation with 3D Warping using Depth Information for FTV. Signal Processing Image Communication 24(1), 265–272 (2009)
Sun, J., Zheng, N.N., Shum, H.Y.: Stereo Matching using Belief Propagation. IEEE Trans. of Pattern Analysis and Machine Intelligence 25(5), 787–800 (2003)
Kim, S.-Y., Lee, E.-K., Ho, Y.-S.: Generation of ROI Enhanced Depth Maps Using Stereoscopic Cameras and a Depth Camera. IEEE Trans. on Broadcasting 54(4), 732–740 (2008)
Zhu, J., Wang, L., Yang, R., Davis, J.: Fusion of Time-of-flight Depth and Stereo for High Accuracy Depth Maps. In: Proc. of IEEE Int’l Conf. Computer Vision Pattern Recognition (2008)
Bartczak, B., Koch, R.: Dense Depth Maps from Low Resolution Time-of-Flight Depth and High Resolution Color Views. In: Bebis, G., et al. (eds.) ISVC 2009, Part II. LNCS, vol. 5876, pp. 228–239. Springer, Heidelberg (2009)
Yang, Q., Yang, R., Davis, J., Nistér, D.: Spatial-Depth Super Resolution for Range Images. In: CVPR 2007 (2007)
Cheng, Y.: Mean Shift, Mode Seeking, and Clustering. IEEE Trans. on Pattern Analysis and Machine Intelligence 17, 790–799 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chiang, JC., Liu, ZF., Lie, WN. (2013). High Quality Novel View Synthesis Based on Low Resolution Depth Image and High Resolution Color Image. In: Jiang, X., Bellon, O.R.P., Goldgof, D., Oishi, T. (eds) Advances in Depth Image Analysis and Applications. WDIA 2012. Lecture Notes in Computer Science, vol 7854. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40303-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-40303-3_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40302-6
Online ISBN: 978-3-642-40303-3
eBook Packages: Computer ScienceComputer Science (R0)