Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices
This addresses the need for efficient image matting in mobile applications, offering a practical solution with weak annotations, though it is incremental in combining existing techniques.
The paper tackles real-time image matting on mobile devices by proposing the Inductive Guided Filter, a lightweight deep learning method that uses weakly annotated masks, and it achieves massive reductions in running time with robust accuracy.
Recently, significant progress has been achieved in deep image matting. Most of the classical image matting methods are time-consuming and require an ideal trimap which is difficult to attain in practice. A high efficient image matting method based on a weakly annotated mask is in demand for mobile applications. In this paper, we propose a novel method based on Deep Learning and Guided Filter, called Inductive Guided Filter, which can tackle the real-time general image matting task on mobile devices. We design a lightweight hourglass network to parameterize the original Guided Filter method that takes an image and a weakly annotated mask as input. Further, the use of Gabor loss is proposed for training networks for complicated textures in image matting. Moreover, we create an image matting dataset MAT-2793 with a variety of foreground objects. Experimental results demonstrate that our proposed method massively reduces running time with robust accuracy.