Abstract | ||
---|---|---|
With the prevalence of smart phones and pocket cameras, photo refocusing has become a basic editing and processing method for its power in interesting object emphasis and photo beautification. However, existing image refocusing methods can hardly be applied on mobile devices due to its high computational cost or the dependence on expensive hardware like light field camera. In this paper, we present a simple but effective method to perform image refocusing automatically and rapidly. The key of our method lies in the utilization of the characteristics of human visual systems. By leveraging current saliency detection methods, we locate the region of interest for a given photo rapidly. Then we calculate its depth map according to the frames captured before shooting. The original image is softly segmented into layers and blurred with different confusion sizes according to the depth map. At last, the blurred layers are softly combined into a refocused photo. Experimental results demonstrate that our method performs outstandingly both in automatic photo refocusing and computational complexity. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/3007669.3007704 | ICIMCS |
Keywords | Field | DocType |
automatic photo refocusing, depth of field, salient object detection | Computer vision,Computer graphics (images),Salience (neuroscience),Effective method,Computer science,Light-field camera,Mobile device,Artificial intelligence,Depth map,Region of interest,Depth of field,Computational complexity theory | Conference |
Citations | PageRank | References |
0 | 0.34 | 4 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Na Liu | 1 | 0 | 0.34 |
Ran Ju | 2 | 108 | 7.87 |
Tongwei Ren | 3 | 328 | 30.22 |
Gangshan Wu | 4 | 275 | 36.63 |