FocusCut: Diving into a Focus View in Interactive Segmentation
By Zheng Lin, Zheng-Peng Duan, Zhao Zhang, Chunle Guo, Ming-Ming Cheng. 2022
68 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Jianfeng Gao
- Yong Jae Lee
- Jianwei Yang
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Cordelia Schmid
In Human-Computer Interaction
Citations in the corpus
- SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (2022, methodology): “Thriving on large datasets, ConvNets [10, 29, 42, 46, 47] have evolved as the dominant architecture for high quality interactive segmentation.”
- Segment Everything Everywhere All at Once (2023, methodology): “For interactive segmentation, we follow previous works [20, 62] to simulate user clicks by comparing the predicted segmentation with the ground-truth one in an automatic way.”