Abstract | ||
---|---|---|
Image blur and noise are difficult to avoid in many situations and can often ruin a photograph. We present a novel image deconvolution algorithm that deblurs and denoises an image given a known shift-invariant blur kernel. Our algorithm uses local color statistics derived from the image as a constraint in a unified framework that can be used for deblurring, denoising, and upsampling. A pixel's color is required to be a linear combination of the two most prevalent colors within a neighborhood of the pixel. This two-color prior has two major benefits: it is tuned to the content of the particular image and it serves to decouple edge sharpness from edge strength. Our unified algorithm for deblurring and denoising out-performs previous methods that are specialized for these individual applications. We demonstrate this with both qualitative results and extensive quantitative comparisons that show that we can out-perform previous methods by approximately 1 to 3 DB. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/CVPRW.2009.5206802 | CVPR: 2009 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-4 |
Keywords | Field | DocType |
image segmentation,kernel,statistics,shift invariant,deconvolution,statistical analysis,filtering,statistical distributions,noise reduction,colored noise,image restoration | Computer vision,Colors of noise,Deblurring,Pattern recognition,Non-local means,Computer science,Deconvolution,Image segmentation,Pixel,Artificial intelligence,Image restoration,Upsampling | Conference |
Volume | Issue | ISSN |
2009 | 1 | 1063-6919 |
Citations | PageRank | References |
85 | 3.53 | 22 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Neel Joshi | 1 | 1155 | 63.95 |
C. Lawrence Zitnick | 2 | 7321 | 332.72 |
Richard Szeliski | 3 | 21300 | 2104.74 |
David Kriegman | 4 | 7693 | 451.96 |