Viet-Anh on Software Logo

What is: MODNet?

SourceMODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

MODNet is a light-weight matting objective decomposition network that can process portrait matting from a single input image in real time. The design of MODNet benefits from optimizing a series of correlated sub-objectives simultaneously via explicit constraints. To overcome the domain shift problem, MODNet introduces a self-supervised strategy based on subobjective consistency (SOC) and a one-frame delay trick to smooth the results when applying MODNet to portrait video sequence.

Given an input image II, MODNet predicts human semantics s_ps\_{p}, boundary details d_pd\_{p}, and final alpha matte α_p\alpha\_{p} through three interdependent branches, S,DS, D, and FF, which are constrained by specific supervisions generated from the ground truth matte α_g\alpha\_{g}. Since the decomposed sub-objectives are correlated and help strengthen each other, we can optimize MODNet end-to-end.