Joint nonlocal sparse representation for depth map super-resolution

Depth image super-resolution reconstruction has gained significant popularity due to its practicability. However, conventional depth image super-resolution reconstruction methods access high frequency information either from a high-resolution depth image database or from a high-resolution color image of the same scene, which is limited in specific applications. In this paper, a novel joint nonlocal sparse representation model is proposed, which is able to capture the interdependency of low-resolution depth and intensity information. As a relative new and not well addressed problem, we reconstruct a high-resolution depth image from a single low-resolution depth image with a low-resolution color image as reference. Experiment results demonstrate that the proposed method outperforms many current state-of-the-art depth map super-resolution approaches on both visual effects and objective image quality.

[1]  Kai-Lung Hua,et al.  Joint trilateral filtering for depth map super-resolution , 2013, 2013 Visual Communications and Image Processing (VCIP).

[2]  Xuming He,et al.  Indoor scene structure analysis for single image depth estimation , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Gerhard Rigoll,et al.  Resolution Enhancement of PMD Range Maps , 2008, DAGM-Symposium.

[4]  Horst Bischof,et al.  Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation , 2013, 2013 IEEE International Conference on Computer Vision.

[5]  Martin Kleinsteuber,et al.  A Joint Intensity and Depth Co-sparse Analysis Model for Depth Map Super-resolution , 2013, 2013 IEEE International Conference on Computer Vision.

[6]  Lei Zhang,et al.  Nonlocally Centralized Sparse Representation for Image Restoration , 2013, IEEE Transactions on Image Processing.

[7]  Lei Zhang,et al.  Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization , 2010, IEEE Transactions on Image Processing.

[8]  Jianjun Yuan,et al.  Improved anisotropic diffusion equation based on new non-local information scheme for image denoising , 2015, IET Comput. Vis..

[9]  Rasmus Larsen,et al.  Fusion of stereo vision and Time-Of-Flight imaging for improved 3D estimation , 2008, Int. J. Intell. Syst. Technol. Appl..

[10]  Christopher Joseph Pal,et al.  Learning Conditional Random Fields for Stereo , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Guosheng Lin,et al.  Deep convolutional neural fields for depth estimation from a single image , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Oscar C. Au,et al.  Depth Map Super-Resolution Using Synthesized View Matching for Depth-Image-Based Rendering , 2012, 2012 IEEE International Conference on Multimedia and Expo Workshops.

[13]  Sebastian Thrun,et al.  LidarBoost: Depth superresolution for ToF 3D shape scanning , 2009, CVPR.

[14]  Sebastian Thrun,et al.  An Application of Markov Random Fields to Range Sensing , 2005, NIPS.

[15]  Michal Irani,et al.  Super-resolution from a single image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[16]  Feng Lin,et al.  Image super-resolution reconstruction by sparse decomposition and scale-invariant feature retrieval in micro-UAV stereo vision , 2014, 11th IEEE International Conference on Control & Automation (ICCA).

[17]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[18]  Abdesselam Bouzerdoum,et al.  Depth image super-resolution using multi-dictionary sparse representation , 2013, 2013 IEEE International Conference on Image Processing.

[19]  David A. Forsyth,et al.  Sparse depth super resolution , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).