Title :
A new virtual view synthesis method using SLIC-based hole filling
Author :
Xiaotian Qiao;Dongxiao Li;Juerong Wu;Lianghao Wang;Ming Zhang
Author_Institution :
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China
Abstract :
This paper presents a new virtual view synthesis method with depth map preprocessing and superpixel segmentation based hole filling. First, in order to reduce the ghosting artifacts caused by the misalignment between depth and texture, the depth image is preprocessed through expanding the regions of foreground objects. Virtual view images are then generated using the depth-image-based rendering algorithm. Second, the original reference color image is segmented into superpixels using simple linear iterative clustering algorithm. Finally, an oriented hole filling method is utilized to fill the disoccluded regions. For each hole pixel, instead of using exemplar patches, a set of candidate superpixels is selected from SLIC segmentations to form the sample space, and the best matching superpixel with the minimum cost is chosen to fill the hole. Experimental results demonstrate that comparing with the state-of-the-art methods, the subjective and objective quality of the synthesized virtual view images are substantially improved with the proposed method.
Keywords :
"Image segmentation","Filling","Color","Image edge detection","Clustering algorithms","Image color analysis","Rendering (computer graphics)"
Conference_Titel :
Signal Processing, Communications and Computing (ICSPCC), 2015 IEEE International Conference on
Print_ISBN :
978-1-4799-8918-8
DOI :
10.1109/ICSPCC.2015.7338852