Name
Abstract | ||
|---|---|---|
Recent years have witnessed the emergence of image decomposition techniques which effectively separate an image into a piecewise smooth base layer and several residual detail layers. However, the intricacy of detail patterns in some cases may result in side-effects including remnant textures, wrongly-smoothed edges, and distorted appearance. We introduce a new way to construct an edge-preserving image decomposition with properties of detail smoothing, edge retention, and shape fitting. Our method has three main steps: suppressing high-contrast details via a windowed variation similarity measure, detecting salient edges to produce an edge-guided image, and fitting the original shape using a weighted least squares framework. Experimental results indicate that the proposed approach can appropriately smooth non-edge regions even when textures and structures are similar in scale. The effectiveness of our approach is demonstrated in the contexts of detail manipulation, HDR tone mapping, and image abstraction. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1007/s41095-015-0006-4 | Computational Visual Media |
Keywords | Field | DocType |
detail suppression, edge extraction, edge-preserving decomposition, shape recovery | Least squares,Computer vision,Residual,Similarity measure,Pattern recognition,Tone mapping,Smoothing,Artificial intelligence,Shape fitting,Mathematics,Piecewise,Salient | Journal |
Volume | Issue | ISSN |
1 | 1 | 2096-0662 |
Citations | PageRank | References |
3 | 0.38 | 26 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| shao pan | 1 | 3 | 0.38 |
| Shouhong Ding | 2 | 23 | 13.20 |
| Lizhuang Ma | 3 | 498 | 100.70 |
| w u yunsheng | 4 | 3 | 0.38 |
| Yong-Jian Wu | 5 | 4 | 0.72 |