Blind Multi-Spectral Image Pan-Sharpening

We address the problem of sharpening low spatial-resolution multi-spectral (MS) images with their associated misaligned high spatial-resolution panchromatic (PAN) image, based on priors on the spatial blur kernel and on the cross-channel relationship. In particular, we formulate the blind pan-sharpening problem within a multi-convex optimization framework using total generalized variation for the blur kernel and local Laplacian prior for the cross-channel relationship. The problem is solved by the alternating direction method of multipliers (ADMM), which alternately updates the blur kernel and sharpens intermediate MS images. Numerical experiments demonstrate that our approach is more robust to large misalignment errors and yields better super resolved MS images compared to state-of-the-art optimization-based and deep-learning-based algorithms.

[1]  Laura Igual,et al.  A Variational Model for P+XS Image Fusion , 2006, International Journal of Computer Vision.

[2]  Chandrajit L. Bajaj,et al.  Blind Hyperspectral-Multispectral Image Fusion via Graph Laplacian Regularization , 2019, ArXiv.

[3]  Jocelyn Chanussot,et al.  A Convex Formulation for Hyperspectral Image Superresolution via Subspace-Based Regularization , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[4]  A. Basarab,et al.  Fast Single Image Super-resolution using a New Analytical Solution for l2-l2 Problems. , 2016, IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.

[5]  Xinghao Ding,et al.  A Variational Pan-Sharpening With Local Gradient Constraints , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jean-Yves Tourneret,et al.  Fast Single Image Super-Resolution Using a New Analytical Solution for $\ell _{2}$ – $\ell _{2}$ Problems , 2016, IEEE Transactions on Image Processing.

[7]  Jian Sun,et al.  Guided Image Filtering , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Carola-Bibiane Schönlieb,et al.  Blind image fusion for hyperspectral imaging with the directional total variation , 2017, ArXiv.

[9]  Hassan Mansour,et al.  Unrolled Projected Gradient Descent for Multi-spectral Image Fusion , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[10]  J. Shewchuk.  An Introduction to the Conjugate Gradient Method Without the Agonizing Pain , 1994 .

[11]  Xinggan Zhang,et al.  Analyzing the group sparsity based on the rank minimization methods , 2016, 2017 IEEE International Conference on Multimedia and Expo (ICME).

[12]  Dehong Liu,et al.  Dictionary learning based pan-sharpening , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  Junfeng Yang,et al.  ALTERNATING DIRECTION ALGORITHMS FOR TOTAL VARIATION DECONVOLUTION IN IMAGE RECONSTRUCTION , 2009 .

[14]  Miguel Á. Carreira-Perpiñán,et al.  Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application , 2013, ArXiv.

[15]  Liangpei Zhang,et al.  Hyperspectral Image Restoration Using Low-Rank Matrix Recovery , 2014, IEEE Transactions on Geoscience and Remote Sensing.