Depth Map Upsampling via Compressive Sensing
- 1 November 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2013 2nd IAPR Asian Conference on Pattern Recognition
Abstract
We propose a new method to enhance the lateral resolution of depth maps with registered high-resolution color images. Inspired by the theory of Compressive Sensing (CS), we formulate the up sampling task as a sparse signal recovery problem. With a reference color image, the low-resolution depth map is converted into suitable sampling data (measurements). The signal recovery problem, defined in a constrained optimization framework, can be efficiently solved with variable splitting and alternating minimization. Experimental results demonstrate the effectiveness of our CS-based method: it competes favorably with other state-of-the-art methods with large up sampling factors and noisy depth inputs.Keywords
This publication has 16 references indexed in Scilit:
- Dense disparity maps from sparse disparity measurementsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- The Split Bregman Method for L1-Regularized ProblemsSIAM Journal on Imaging Sciences, 2009
- Stereoscopic inpainting: Joint color and depth completion from stereo imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- An Introduction To Compressive SamplingIEEE Signal Processing Magazine, 2008
- A New Alternating Minimization Algorithm for Total Variation Image ReconstructionSIAM Journal on Imaging Sciences, 2008
- Joint bilateral upsamplingPublished by Association for Computing Machinery (ACM) ,2007
- Evaluation of Cost Functions for Stereo MatchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Sparsity and incoherence in compressive samplingInverse Problems, 2007
- Compressed sensingIEEE Transactions on Information Theory, 2006
- Uncertainty principles and ideal atomic decompositionIEEE Transactions on Information Theory, 2001