dugMatting: Decomposed-Uncertainty-Guided Matting
This work addresses the time-consuming and user-expertise-dependent nature of image matting for image and video editing, though it appears incremental as it builds upon existing matting algorithms.
The paper tackles the problem of image matting, which requires additional user inputs like trimaps or scribbles, by proposing a decomposed-uncertainty-guided algorithm that reduces the need for expert user interaction. The method significantly improves original matting algorithms in efficiency and efficacy, as validated by extensive quantitative and qualitative results.
Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing. Due to the highly ill-posed issue, additional inputs, typically user-defined trimaps or scribbles, are usually needed to reduce the uncertainty. Although effective, it is either time consuming or only suitable for experienced users who know where to place the strokes. In this work, we propose a decomposed-uncertainty-guided matting (dugMatting) algorithm, which explores the explicitly decomposed uncertainties to efficiently and effectively improve the results. Basing on the characteristic of these uncertainties, the epistemic uncertainty is reduced in the process of guiding interaction (which introduces prior knowledge), while the aleatoric uncertainty is reduced in modeling data distribution (which introduces statistics for both data and possible noise). The proposed matting framework relieves the requirement for users to determine the interaction areas by using simple and efficient labeling. Extensively quantitative and qualitative results validate that the proposed method significantly improves the original matting algorithms in terms of both efficiency and efficacy.