MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition

TL;DR

MODNet is a lightweight, real-time portrait matting network that eliminates the need for auxiliary inputs, using explicit constraints and novel modules to achieve high accuracy and efficiency suitable for practical applications.

Contribution

The paper introduces MODNet, a novel trimap-free portrait matting model that employs objective decomposition, an efficient ASPP module, and a self-supervised strategy for domain adaptation.

Findings

Runs at 67 FPS on a 1080Ti GPU

Outperforms previous trimap-free methods on benchmark datasets

Effective in real-world portrait and video applications

Abstract

Existing portrait matting methods either require auxiliary inputs that are costly to obtain or involve multiple stages that are computationally expensive, making them less suitable for real-time applications. In this work, we present a light-weight matting objective decomposition network (MODNet) for portrait matting in real-time with a single input image. The key idea behind our efficient design is by optimizing a series of sub-objectives simultaneously via explicit constraints. In addition, MODNet includes two novel techniques for improving model efficiency and robustness. First, an Efficient Atrous Spatial Pyramid Pooling (e-ASPP) module is introduced to fuse multi-scale features for semantic estimation. Second, a self-supervised sub-objectives consistency (SOC) strategy is proposed to adapt MODNet to real-world data to address the domain shift problem common to trimap-free methods. MODNet is easy to be trained in an end-to-end manner. It is much faster than contemporaneous methods and runs at 67 frames per second on a 1080Ti GPU. Experiments show that MODNet outperforms prior trimap-free methods by a large margin on both Adobe Matting Dataset and a carefully designed photographic portrait matting (PPM-100) benchmark proposed by us. Further, MODNet achieves remarkable results on daily photos and videos. Our code and models are available at https://github.com/ZHKKKe/MODNet, and the PPM-100 benchmark is released at https://github.com/ZHKKKe/PPM.