论文标题
探索统一有效图像垫的交互式指南
Exploring the Interactive Guidance for Unified and Effective Image Matting
论文作者
论文摘要
最新的图像矩阵研究正在发展，旨在提出无构图或交互式方法，以实现完整的复杂图像效果任务。尽管避免了Trimap注释的广泛劳动，但现有方法仍然存在两个局限性：（1）对于具有多个对象的单个图像，必须提供额外的交互信息来帮助确定垫片目标； （2）对于透明对象，与不透明的对象相比，从RGB图像中α哑光的准确回归要困难得多。在这项工作中，我们提出了一种名为UIM的统一交互式图像矩阵方法，该方法解决了任何情况下的局限性并实现了令人满意的底漆结果。具体而言，UIM利用多种类型的用户交互来避免多个MATTING目标的歧义，我们将详细的注释类型的利弊进行比较。为了统一透明和不透明对象的底漆性能，我们将图像垫子分为两个阶段，即前景分割和透明度预测。此外，我们设计了一个多尺度的细心融合模块，以减轻边界区域的模糊性。实验结果表明，UIM在组成-1K测试集和合成统一数据集上实现了最先进的性能。
Recent image matting studies are developing towards proposing trimap-free or interactive methods for complete complex image matting tasks. Although avoiding the extensive labors of trimap annotation, existing methods still suffer from two limitations: (1) For the single image with multiple objects, it is essential to provide extra interaction information to help determining the matting target; (2) For transparent objects, the accurate regression of alpha matte from RGB image is much more difficult compared with the opaque ones. In this work, we propose a Unified Interactive image Matting method, named UIM, which solves the limitations and achieves satisfying matting results for any scenario. Specifically, UIM leverages multiple types of user interaction to avoid the ambiguity of multiple matting targets, and we compare the pros and cons of different annotation types in detail. To unify the matting performance for transparent and opaque objects, we decouple image matting into two stages, i.e., foreground segmentation and transparency prediction. Moreover, we design a multi-scale attentive fusion module to alleviate the vagueness in the boundary region. Experimental results demonstrate that UIM achieves state-of-the-art performance on the Composition-1K test set and a synthetic unified dataset.
