Depth map Super-Resolution based on joint dictionary learning
- 480 Downloads
Although Time-of-Flight (ToF) camera can provide real-time depth information from a real scene, the resolution of depth map captured by ToF camera is rather limited compared to HD color cameras, and thus it cannot be directly used in 3D reconstruction. In order to handle this problem, this paper proposes a novel compressive sensing (CS) and dictionary learning based depth map super-resolution (SR) method, which transforms a low resolution depth map to a high resolution depth map. Different from previous depth map SR methods, this algorithm uses a joint dictionary learning method with both low and high resolution depth maps, and this method also builds a sparse vector classification method which is used in depth map SR. Experimental results show that the proposed method outperforms state-of-the-art methods for depth map super-resolution.
KeywordsDepth map Super-resolution Joint dictionary learning Sparse expression
This work was supported in part by the National Natural Science Foundation of China (Grant No. 61271338), the National High Technology Research and Development Program (863) of China (Grant No. 2012AA011505), the Zhejiang Provincial Natural Science Foundation of China (Grant No. Q14F010020), and the Open Projects Program of National Laboratory of Pattern Recognition of China (Grant No. 201306308).
- 1.3dv systems, z-cam, http://www.3dvsystems.com
- 4.Candès EJ (2006) Compressive sampling. Proc Int Congr Math Madrid Spain 3:1433–1452Google Scholar
- 5.Canesta Inc (2006) Canestavision electronic perception development kit, http://www.canesta.com/
- 6.Chang H, Yeung D, Xiong Y (2004) Super-resolution through neighbor embedding. IEEE Conference on Computer Vision and Pattern Recognition, 1:1–8Google Scholar
- 12.Glasner D, Bagon S, Irani M (2009) “Super-resolution from a single image” ICCV pp. 349–356Google Scholar
- 16.PMD camcube (2009) http://www.pmdtec.com/
- 19.Scharstein D and Szeliski R (2002) Middlebury stereo evaluation-version 2, http://vision.middlebury.edu/stereo/eval
- 23.Wu F, Lu X, Zhang Y, Zhang Z, Yan S, Zhuang Y (2013) Cross-media semantic representation via Bi-directional learning to rank. Proc 2013 ACM Int Conf Multimed (ACM Multimedia, Full Paper) 877–886Google Scholar
- 25.Xu Z, Schwarte R, Heinol H, Buxbaum B, Ringbeck T (1998) Smart pixel C photonic mixer device (pmd), M2VIP 1998 - Int Conf Mechatron Mach Vision Pract 259–264Google Scholar