# Infusing Definiteness into Randomness: Rethinking Composition Styles for Deep Image Matting

arXiv: https://arxiv.org/abs/2212.13517 · HTML: https://mlsanity.com/paper/2212.13517/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 27 Dec 2022.

## Builds on (most cited first, 13 of 13)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Density-aware Single Image De-raining using a Multi-stream Dense Network](https://mlsanity.com/paper/1802.07412/) (2018)
- [Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection](https://mlsanity.com/paper/1708.01642/) (2017)
- [Deep Image Matting](https://mlsanity.com/paper/1703.03872/) (2017)
- [MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition](https://mlsanity.com/paper/2011.11961/) (2020)
- [Indices Matter: Learning to Index for Deep Image Matting](https://mlsanity.com/paper/1908.00672/) (2019)
- [Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation](https://mlsanity.com/paper/1909.09725/) (2019)
- [Natural Image Matting via Guided Contextual Attention](https://mlsanity.com/paper/2001.04069/) (2020)
- [Deep Automatic Natural Image Matting](https://mlsanity.com/paper/2107.07235/) (2021)
- [MatteFormer: Transformer-Based Image Matting via Prior-Tokens](https://mlsanity.com/paper/2203.15662/) (2022)
- [Learning Affinity-Aware Upsampling for Deep Image Matting](https://mlsanity.com/paper/2011.14288/) (2020)
- [Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation](https://mlsanity.com/paper/2201.06889/) (2022)

## Built on by (most cited first, 2 of 2)

- [Data Optimization in Deep Learning: A Survey](https://mlsanity.com/paper/2310.16499/) (2023)
- [Capture Stage Matting: Challenges, Approaches, and Solutions for Offline and Real-Time Processing](https://mlsanity.com/paper/2507.07623/) (2025)

## Abstract (arXiv)

We study the composition style in deep image matting, a notion that characterizes a data generation flow on how to exploit limited foregrounds and random backgrounds to form a training dataset. Prior art executes this flow in a completely random manner by simply going through the foreground pool or by optionally combining two foregrounds before foreground-background composition. In this work, we first show that naive foreground combination can be problematic and therefore derive an alternative formulation to reasonably combine foregrounds. Our second contribution is an observation that matting performance can benefit from a certain occurrence frequency of combined foregrounds and their associated source foregrounds during training. Inspired by this, we introduce a novel composition style that binds the source and combined foregrounds in a definite triplet. In addition, we also find that different orders of foreground combination lead to different foreground patterns, which further inspires a quadruplet-based composition style. Results under controlled experiments on four matting baselines show that our composition styles outperform existing ones and invite consistent performance improvement on both composited and real-world datasets. Code is available at: https://github.com/coconuthust/composition_styles