| Paper: | TP-P4.4 |
| Session: | Image and Video Segmentation V |
| Time: | Tuesday, September 18, 14:30 - 17:10 |
| Presentation: |
Poster
|
| Title: |
BACKGROUND CUTOUT WITH AUTOMATIC OBJECT DISCOVERY |
| Authors: |
David Liu; Carnegie Mellon University | | |
| | Tsuhan Chen; Carnegie Mellon University | | |
| Abstract: |
We present a novel approach to background cutout for image editing. We show how background cutout can be achieved even without any user labeling. This is in contrast to current methods, where the user needs to label each image separately. Our method uses automatic object discovery methods to provide location and scale estimates of the object of interest; these estimates then provide seeds for initializing the color distributions of a segmentation algorithm. We show that our approach can achieve similar performance as traditional methods that require users to specify a bounding box for the object of interest in each image. |
