Fast and Robust Multi-Frame Super-Resolution
By Sina Farsiu, D. Robinson, Michael Elad, Peyman Milanfar. IEEE Transactions on Image Processing, 2004
369 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/f1a9945b6e55df3a67c469485b544684b24817ee
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Dacheng Tao
- Luc Van Gool
- Lei Zhang
- Radu Timofte
- Xinbo Gao
- Xuelong Li
- Chen Change Loy
- Peyman Milanfar
In Media Technology
- Thomas Baltzer Moeslund
- Kamal Nasrollahi
- Xinbo Gao
- Xuelong Li
- Dacheng Tao
- Peyman Milanfar
- Michael Elad
- Matan Protter
Citations in the corpus
- Advances and challenges in super‐resolution (2004, methodology): “(11) We previously proposed (Farsiu et al., 2004) a method for applying a steepest descent algorithm to minimize this cost function.”
- Super-resolution: a comprehensive survey (2014, background): “– [155], [156], [157], [158], [160] change the imaging”
- Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding (2012, methodology): “Example-based SR algorithms belong to this family: the learning process is performed locally, by trying to infer the local HR details through the use of small “examples”.”
- Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression (2012, methodology): “The multi-image-based SR approaches assume that the high frequency details lost in an LR image are split across a set of LR images with sub-pixel misalignments from the same scene, including frequency domain methods [1], [6], [7] and spatial domain methods [8]–[12].”
- Super-Resolution Without Explicit Subpixel Motion Estimation (2009, methodology): “Simple super-resolution example using 3-D ISKR: (a) the original image, (b) one of 9 low resolution images generated by blurring with a 3 3 uniform PSF, spatially downsampling with a factor of 3:1, and adding white Gaussian noise with standard deviation , (c) an upscaled image by Lancsoz (single fra”
- Kernel Regression for Image Processing and Reconstruction (2007, methodology): “low-resolution images are fused (interlaced) onto a high-resolution grid [2].”
- Multiframe demosaicing and super-resolution of color images (2006, methodology): “In recent years, more sophisticated SR methods were developed (see [3] and [6]–[10] as representative works).”