Title :
Synthesis-guided depth super resolution
Author :
Huijin Lv ; Yongbing Zhang ; Kai Li ; Xingzheng Wang ; Huiming Xuan ; Qionghai Dai
Author_Institution :
Shenzhen Key Lab. of Broadband Network & Multimedia, Tsinghua Univ., Shenzhen, China
Abstract :
Depth map, as important auxiliary information in 3D procession, is used to synthesize virtual view rather than exhibition. Inspired by this, a synthesis-guided depth super resolution (SGDSR) algorithm is proposed. Employing the synthesis error between virtual view and corresponding original one as the criteria, the best super-resolved result is selected among numerous candidate super resolution (SR) results. To fully exploit varying property within different regions of an image, a patch-based SGDSR is further devised in this paper. Experimental results demonstrate the effectiveness of our method subjectively and objectively on both single view and two views platform based on depth-image-based rendering (DIBR).
Keywords :
image enhancement; image resolution; rendering (computer graphics); 3D procession; DIBR; SGDSR algorithm; depth-image-based rendering; patch-based SGDSR; synthesis error; synthesis-guided depth super resolution; virtual view; Educational institutions; Image edge detection; Image resolution; Joints; PSNR; Rendering (computer graphics); Three-dimensional displays; Super resolution; depth map; depth-image-based rendering; synthesis-guided; view synthesis;
Conference_Titel :
Visual Communications and Image Processing Conference, 2014 IEEE
DOI :
10.1109/VCIP.2014.7051520
