Abstract | ||
---|---|---|
Aliasing is a common artifact in low-resolution (LR) images generated by a downsampling process. Recovering the original high-resolution image from its LR counterpart while at the same time removing the aliasing artifacts is a challenging image interpolation problem. Since a natural image normally contains redundant similar patches, the values of missing pixels can be available at texture-relevant LR pixels. Based on this, we propose an iterative multiscale semilocal interpolation method that can effectively address the aliasing problem. The proposed method estimates each missing pixel from a set of texture-relevant semilocal LR pixels with the texture similarity iteratively measured from a sequence of patches of varying sizes. Specifically, in each iteration, top texture-relevant LR pixels are used to construct a data fidelity term in a maximum a posteriori estimation, and a bilateral total variation is used as the regularization term. Experimental results compared with existing interpolation methods demonstrate that our method can not only substantially alleviate the aliasing problem but also produce better results across a wide range of scenes both in terms of quantitative evaluation and subjective visual quality. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/TIP.2011.2165290 | IEEE Transactions on Image Processing |
Keywords | Field | DocType |
challenging image interpolation problem,subjective visual quality,lr counterpart,antialiasing,image interpolation,data fidelity term,missing pixel estimation,interpolation,aliasing problem,quantitative evaluation,maximum a posteriori estimation,bilateral total variation,image resolution,maximum likelihood estimation,texture-relevant lr pixel,interpolation method,image interpolation problem,multiscale semilocal interpolation,iterative multiscale,top texture-relevant lr pixel,aliasing artifact,missing pixel,semilocal,iterative multiscale semilocal interpolation,low-resolution images,image texture,iterative multiscale semilocal interpolation method,downsampling process,iterative methods,texture-relevant lr pixels,natural image,regularization term,estimation,low resolution,iteration method,materials,total variation,noise reduction,edge detection | Computer vision,Pattern recognition,Image texture,Interpolation,Aliasing,Artificial intelligence,Pixel,Maximum a posteriori estimation,Upsampling,Image resolution,Image scaling,Mathematics | Journal |
Volume | Issue | ISSN |
21 | 2 | 1941-0042 |
Citations | PageRank | References |
10 | 0.51 | 17 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kai Guo | 1 | 15 | 1.94 |
Xiaokang Yang | 2 | 3581 | 238.09 |
Hongyuan Zha | 3 | 6703 | 422.09 |
Weiyao Lin | 4 | 732 | 68.05 |
Yu Song | 5 | 356 | 52.74 |