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

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

55 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings of the 36th AAAI Conference on Artificial Intelligence
Place of PublicationPalo Alto, California
PublisherAAAI Press
Pages1140-1147
Volume36
ISBN (print)1577358767, 9781577358763
Publication statusPublished - 2022

Publication series

NameProceedings of the AAAI Conference on Artificial Intelligence
Number1
Volume36
ISSN (Print)2159-5399
ISSN (electronic)2374-3468

Conference

Title36th AAAI Conference on Artificial Intelligence (AAAI-22)
LocationVirtual
Period22 February - 1 March 2022

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. Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

Research Area(s)

  • Computer Vision (CV)

Citation Format(s)

MODNet: Real-Time Trimap-free Portrait Matting via Objective Decomposition. / Ke, Zhanghan; Sun, Jiayu; Li, Kaican et al.
Proceedings of the 36th AAAI Conference on Artificial Intelligence. Vol. 36 Palo Alto, California: AAAI Press, 2022. p. 1140-1147 (Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 36, No. 1).

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review