Multiframe demosaicing and super-resolution of color images

By Sina Farsiu, Michael Elad, Peyman Milanfar. IEEE Transactions on Image Processing, 2006

352 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Super-resolution: a comprehensive survey (2014, background): “[63], [64], [156], [210], [225], [226], [227], [278], [334], [387], [427], [463] have been developed mainly for generating a super-resolved video from an LR video (video to video SR), and treat the problem as a state esti-”
Analysis versus synthesis in signal priors (2006, methodology): “Highly organized neighborliness patterns.”
Kernel Regression for Image Processing and Reconstruction (2007, methodology): “To produce better color estimates, following [41], first we transferred this RGB image to the YCrCb representation.”
A super-resolution reconstruction algorithm for surveillance images (2010, methodology): “Based on these basic reconstruction models, researchers have produced many extended algorithms, such as the joint formulation of reconstruction and registration [20–23], algorithms for multi-spectral and color [24,25], hyper-spectral [26], and compressed [27,28] sequence, etc.”
Burst photography for high dynamic range and low-light imaging on mobile cameras (2016, methodology): “In the academic literature, burst fusion methods based on raw imagery [Farsiu et al. 2006; Heide et al. 2014] are relatively uncommon.”