Human matting is a foundation task in image and video processing, where human
foreground pixels are extracted from the input. Prior works either improve the
accuracy by additional guidance or improve the temporal consistency of a single
instance across frames. We propose a new framework MaGGIe, Masked Guided
Gradual Human Instance Matting, which predicts alpha mattes progressively for
each human instances while maintaining the computational cost, precision, and
consistency. Our method leverages modern architectures, including transformer
attention and sparse convolution, to output all instance mattes simultaneously
without exploding memory and latency. Although keeping constant inference costs
in the multiple-instance scenario, our framework achieves robust and versatile
performance on our proposed synthesized benchmarks. With the higher quality
image and video matting benchmarks, the novel multi-instance synthesis approach
from publicly available sources is introduced to increase the generalization of
models in real-world scenarios.

我们提出了一种新的框架 MaGGIe，即遮蔽引导逐渐人物实例抠图（Masked Guided Gradual Human Instance Matting），该框架能够在保持计算成本、精确度和一致性的同时逐步预测每个人物实例的透明度抠图。我们的方法利用现代架构，如 Transformer 注意力和稀疏卷积，同时输出所有实例的抠图，而不会发生内存和延迟问题。尽管在多实例情景下保持恒定的推理成本，我们的框架在我们提出的综合基准测试中实现了稳健而灵活的性能。通过使用更高质量的图像和视频抠图基准，引入了来自公开可用源的新型多实例综合方法，以增加模型在现实世界场景中的泛化能力。