Methods › Computer Vision › Portrait Matting Models › MODNet
MODNet
Introduced by Zhanghan Ke et al. in MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 I, MODNet predicts human semantics sₚ, boundary details dₚ, and final alpha matte αₚ through three interdependent branches, S, D, and F, which are constrained by specific supervisions generated from the ground truth matte α_g. Since the decomposed sub-objectives are correlated and help strengthen each other, we can optimize MODNet end-to-end.
Papers archive 2025-07-28
4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
SGM-Net: Semantic Guided Matting Net 16 Aug 2022 · 0 repositories · arXiv:2208.07496
-
MODNet-V: Improving Portrait Video Matting via Background Restoration 24 Sep 2021 · 1 repository · arXiv:2109.11818
-
Alpha Matte Generation from Single Input for Portrait Matting 6 Jun 2021 · 0 repositories · arXiv:2106.03210
-
MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition 24 Nov 2020 · 9 repositories · arXiv:2011.11961
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Image Matting | 4 |
| GPU | 2 |
| Video Matting | 2 |
| Image Generation | 1 |
| Segmentation | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections