Abstract | ||
---|---|---|
The full-image based kernel estimation strategy is usually susceptible by the smooth and fine-scale background regions impacting and it is time-consuming for large-size image deblurring. Since not all the pixels in the blurred image are informative and it is frequent to restore human-interested objects in the foreground rather than background, we propose a novel concept “SalientPatch” to denote informative regions for better blur kernel estimation without user guidance by computing three cues (objectness probability, structure richness and local contrast). Although these cues are not new, it is innovative to integrate and complement each other in motion blur restoration. Experiments demonstrate that our SalientPatch-based deblurring algorithm can significantly speed up the kernel estimation and guarantee high-quality recovery for large-size blurry images as well. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/s11042-018-6009-2 | Multimedia Tools Appl. |
Keywords | Field | DocType |
Deblurring, SalientPatch, Kernel estimation, Segmentation, Large-size | Computer vision,Deblurring,Pattern recognition,Segmentation,Computer science,Motion blur,Pixel,Artificial intelligence,Kernel density estimation,Speedup | Journal |
Volume | Issue | ISSN |
77 | 21 | 1380-7501 |
Citations | PageRank | References |
1 | 0.35 | 16 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chengcheng Ma | 1 | 1 | 1.36 |
Jiguang Zhang | 2 | 3 | 1.72 |
Shibiao Xu | 3 | 91 | 16.31 |
Weiliang Meng | 4 | 2 | 2.38 |
Runping Xi | 5 | 1 | 1.36 |
G. Hemantha Kumar | 6 | 222 | 27.92 |
Xiaopeng Zhang | 7 | 372 | 36.34 |