FocusCut: Diving Into a Focus View in Interactive Segmentation

Zheng Lin, Zheng-Peng Duan, Zhao Zhang, Chun-Le Guo, Ming-Ming Cheng; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 2637-2646

Abstract


Interactive image segmentation is an essential tool in pixel-level annotation and image editing. To obtain a high-precision binary segmentation mask, users tend to add interaction clicks around the object details, such as edges and holes, for efficient refinement. Current methods regard these repair clicks as the guidance to jointly determine the global prediction. However, the global view makes the model lose focus from later clicks, and is not in line with user intentions. In this paper, we dive into the view of clicks' eyes to endow them with the decisive role in object details again. To verify the necessity of focus view, we design a simple yet effective pipeline, named FocusCut, which integrates the functions of object segmentation and local refinement. After obtaining the global prediction, it crops click-centered patches from the original image with adaptive scopes to refine the local predictions progressively. Without user perception and parameters increase, our method has achieved state-of-the-art results. Extensive experiments and visualized results demonstrate that FocusCut makes hyper-fine segmentation possible for interactive image segmentation.

Related Material


[pdf]
[bibtex]
@InProceedings{Lin_2022_CVPR, author = {Lin, Zheng and Duan, Zheng-Peng and Zhang, Zhao and Guo, Chun-Le and Cheng, Ming-Ming}, title = {FocusCut: Diving Into a Focus View in Interactive Segmentation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {2637-2646} }