Interactive Image Segmentation Method

What is it about?

This paper proposes a practical interactive image segmentation tool similar to the Quick Selection Tool integrated in the famous Adobe Photoshop. The tool raised in this paper can help you to get satisfactory binary segmentation results efficiently.

Featured Image

Why is it important?

We propose an efficacious appearance separation model for interactive binary segmentation, which incorporates the difference between foreground and background color models and the difference of corresponding geodesic models into the popular Dense CRF framework. Our method can adaptively set relevant parameter values in this framework according to the characteristics of target images in a per-image manner, therefore, it gets rid of the dependence on specific datasets. After accomplishing a mean-field inference, we are able to get satisfactory results without the time-consuming parameter learning process and multiple iterative optimizations. Overall, our approach is highly efficient and mitigates the contradiction between accuracy and segmentation efficiency. In addition, our approach reduces the efforts of scribble-style interaction from users.

Perspectives