Adaptive preprocessing and combination techniques for light field image rendering

Image rendering is to construct a large image from several smaller images. It is very important for stereo image generating and light filed image processing. In this paper, we propose several techniques to improve the performance of image rendering. When perform disparity estimation, higher weights are assigned for edge and corner pixels to increase their effects. When perform linear combination, the weight functions with different fractional powers are assigned for different layers. Moreover, the adaptive disparity estimation mechanism is also applied for image rendering. Simulations show that, with these techniques the performance of image rendering is much better that of conventional methods.

[1]  Patrick Pérez,et al.  Poisson image editing , 2003, ACM Trans. Graph..

[2]  A. Lumsdaine,et al.  Focused Plenoptic Camera and Rendering Focused Plenoptic Camera and Rendering , 2010 .

[3]  Irfan Essa,et al.  Texture optimization for example-based synthesis , 2005, SIGGRAPH 2005.

[4]  Andrew Lumsdaine,et al.  Superresolution with the focused plenoptic camera , 2011, Electronic Imaging.

[5]  Matthew A. Brown,et al.  Recognising panoramas , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  Edward H. Adelson,et al.  A multiresolution spline with application to image mosaics , 1983, TOGS.