MaGGIe: Masked Guided Gradual Human Instance Matting

arXiv:2404.16035v1 Announce Type: new
Abstract: 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 …

abstract accuracy arxiv cs.ai cs.cv foundation framework guidance human image instance pixels prior processing temporal type video video processing