# Privacy-Preserving Portrait Matting

arXiv: https://arxiv.org/abs/2104.14222 · HTML: https://mlsanity.com/paper/2104.14222/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 29 Apr 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [Auditing Differentially Private Machine Learning: How Private is Private SGD?](https://mlsanity.com/paper/2006.07709/) (2020)
- [Real-Time High-Resolution Background Matting](https://mlsanity.com/paper/2012.07810/) (2020)
- [Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things](https://mlsanity.com/paper/2011.08612/) (2020)
- [Background Matting: The World is Your Green Screen](https://mlsanity.com/paper/2004.00626/) (2020)
- [Indices Matter: Learning to Index for Deep Image Matting](https://mlsanity.com/paper/1908.00672/) (2019)
- [Mask Guided Matting via Progressive Refinement Network](https://mlsanity.com/paper/2012.06722/) (2020)
- [A Study of Face Obfuscation in ImageNet](https://mlsanity.com/paper/2103.06191/) (2021)
- [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)
- [Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?](https://mlsanity.com/paper/1904.05506/) (2019)
- [Semantic Human Matting](https://mlsanity.com/paper/1809.01354/) (2018)
- [Information-Flow Matting](https://mlsanity.com/paper/1707.05055/) (2017)
- [AlphaGAN: Generative adversarial networks for natural image matting](https://mlsanity.com/paper/1807.10088/) (2018)
- [F, B, Alpha Matting](https://mlsanity.com/paper/2003.07711/) (2020)
- [Boosting Semantic Human Matting with Coarse Annotations](https://mlsanity.com/paper/2004.04955/) (2020)
- [Towards High Performance Human Keypoint Detection](https://mlsanity.com/paper/2002.00537/) (2020)
- [Privacy Protection in Street-View Panoramas using Depth and Multi-View Imagery](https://mlsanity.com/paper/1903.11532/) (2019)
- [Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption](https://mlsanity.com/paper/1704.02203/) (2017)

## Built on by (most cited first, 30 of 60)

- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?](https://mlsanity.com/paper/2403.06090/) (2024)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [Deep Automatic Natural Image Matting](https://mlsanity.com/paper/2107.07235/) (2021)
- [Matte Anything: Interactive Natural Image Matting with Segment Anything Models](https://mlsanity.com/paper/2306.04121/) (2023)
- [DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks](https://mlsanity.com/paper/2502.17157/) (2025)
- [Generative Omnimatte: Learning to Decompose Video into Layers](https://mlsanity.com/paper/2411.16683/) (2024)
- [Rethinking Portrait Matting with Privacy Preserving](https://mlsanity.com/paper/2203.16828/) (2022)
- [Referring Image Matting](https://mlsanity.com/paper/2206.05149/) (2022)
- [MaGGIe: Masked Guided Gradual Human Instance Matting](https://mlsanity.com/paper/2404.16035/) (2024)
- [Ethical Considerations for Responsible Data Curation](https://mlsanity.com/paper/2302.03629/) (2023)
- [ZIM: Zero-Shot Image Matting for Anything](https://mlsanity.com/paper/2411.00626/) (2024)
- [DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation](https://mlsanity.com/paper/2403.06168/) (2024)
- [Matting by Generation](https://mlsanity.com/paper/2407.21017/) (2024)
- [Robust Human Matting via Semantic Guidance](https://mlsanity.com/paper/2210.05210/) (2022)
- [Deep Image Matting: A Comprehensive Survey](https://mlsanity.com/paper/2304.04672/) (2023)
- [Does Image Anonymization Impact Computer Vision Training?](https://mlsanity.com/paper/2306.05135/) (2023)
- [DAViD: Data-efficient and Accurate Vision Models from Synthetic Data](https://mlsanity.com/paper/2507.15365/) (2025)
- [AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning](https://mlsanity.com/paper/2507.09308/) (2025)
- [MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator](https://mlsanity.com/paper/2512.11782/) (2025)
- [Exposure Correction Model to Enhance Image Quality](https://mlsanity.com/paper/2204.10648/) (2022)
- [Revisiting Context Aggregation for Image Matting](https://mlsanity.com/paper/2304.01171/) (2023)
- [WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users](https://mlsanity.com/paper/2404.17063/) (2024)
- [FiffDepth: Feed-forward Transformation of Diffusion-Based Generators for Detailed Depth Estimation](https://mlsanity.com/paper/2412.00671/) (2024)
- [Edit2Perceive: Image Editing Diffusion Models Are Strong Dense Perceivers](https://mlsanity.com/paper/2511.18673/) (2025)
- [THFM: A Unified Video Foundation Model for 4D Human Perception and Beyond](https://mlsanity.com/paper/2603.25892/) (2026)
- [Adversarially-Guided Portrait Matting](https://mlsanity.com/paper/2305.02981/) (2023)
- [dugMatting: Decomposed-Uncertainty-Guided Matting](https://mlsanity.com/paper/2306.01452/) (2023)
- [Lightweight Portrait Matting via Regional Attention and Refinement](https://mlsanity.com/paper/2311.03770/) (2023)
- [End-to-End Human Instance Matting](https://mlsanity.com/paper/2403.01510/) (2024)

## Abstract (arXiv)

Recently, there has been an increasing concern about the privacy issue raised by using personally identifiable information in machine learning. However, previous portrait matting methods were all based on identifiable portrait images. To fill the gap, we present P3M-10k in this paper, which is the first large-scale anonymized benchmark for Privacy-Preserving Portrait Matting. P3M-10k consists of 10,000 high-resolution face-blurred portrait images along with high-quality alpha mattes. We systematically evaluate both trimap-free and trimap-based matting methods on P3M-10k and find that existing matting methods show different generalization capabilities when following the Privacy-Preserving Training (PPT) setting, i.e., training on face-blurred images and testing on arbitrary images. To devise a better trimap-free portrait matting model, we propose P3M-Net, which leverages the power of a unified framework for both semantic perception and detail matting, and specifically emphasizes the interaction between them and the encoder to facilitate the matting process. Extensive experiments on P3M-10k demonstrate that P3M-Net outperforms the state-of-the-art methods in terms of both objective metrics and subjective visual quality. Besides, it shows good generalization capacity under the PPT setting, confirming the value of P3M-10k for facilitating future research and enabling potential real-world applications. The source code and dataset are available at https://github.com/JizhiziLi/P3M