An object-based approach to plenoptic video processing

Image-based rendering (IBR) is an emerging technology for photo-realistic rendering of scenes from a collection of densely sampled images and videos. Recently, an object-based approach for a class of dynamic image-based representations called plenoptic videos was proposed in order to improve the rendering quality in large environment. Since images and videos are special cases of the plenoptic function, many conventional image processing algorithms such as coding, segmentation, etc have similar analogy in IBR. This paper is devoted to the extension of some commonly used image processing algorithms to IBR using the object-based approach and their possible applications. Experimental results using plenoptic videos as an example are also given to illustrate the basic concept.