Fast and robust multiframe super resolution

• Published in: IEEE transactions on image processing Vol. 13; no. 10; pp. 1327 - 1344
• Main Authors: Farsiu, S., Robinson, M.D., Elad, M., Milanfar, P.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01-10-2004; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Cameras; Computational modeling; Computer Graphics; Computer science; control theory; systems; Computer Simulation; Exact sciences and technology; Frequency domain analysis; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image processing; Image reconstruction; Image resolution; Information Storage and Retrieval - methods; Information, signal and communications theory; Layout; Lenses; Mathematical models; Motion estimation; Noise; Noise robustness; Norms; Numerical Analysis, Computer-Assisted; Optimization; Pattern Recognition, Automated; Pattern recognition. Digital image processing. Computational geometry; Regularization; Reproducibility of Results; Sensitivity and Specificity; Signal processing; Signal Processing, Computer-Assisted; Spatial resolution; Subtraction Technique; Telecommunications and information theory; Utilities; Filtering; Motion estimation; Noise reduction; Superresolution; L1 approximation; regularization; multiframe; super resolution; Image restoration; enhancement; Image reconstruction; Regularization method; Bilateral filter; robust estimation; total variation (TV); Image enhancement; deblurring
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2004.834669

Super-resolution reconstruction produces one or a set of high-resolution images from a set of low-resolution images. In the last two decades, a variety of super-resolution methods have been proposed. These methods are usually very sensitive to their assumed model of data and noise, which limits their utility. This paper reviews some of these methods and addresses their shortcomings. We propose an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models. This computationally inexpensive method is robust to errors in motion and blur estimation and results in images with sharp edges. Simulation results confirm the effectiveness of our method and demonstrate its superiority to other super-resolution methods.