# Rethinking Portrait Matting with Privacy Preserving

arXiv: https://arxiv.org/abs/2203.16828 · HTML: https://mlsanity.com/paper/2203.16828/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 65 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (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)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [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)
- [ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias](https://mlsanity.com/paper/2106.03348/) (2021)
- [A Hybrid Approach to Privacy-Preserving Federated Learning](https://mlsanity.com/paper/1812.03224/) (2018)
- [Real-Time High-Resolution Background Matting](https://mlsanity.com/paper/2012.07810/) (2020)
- [Deep Image Matting](https://mlsanity.com/paper/1703.03872/) (2017)
- [ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond](https://mlsanity.com/paper/2202.10108/) (2022)
- [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)
- [Bridging Composite and Real: Towards End-to-end Deep Image Matting](https://mlsanity.com/paper/2010.16188/) (2020)
- [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)

## Built on by (most cited first, 25 of 25)

- [What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?](https://mlsanity.com/paper/2403.06090/) (2024)
- [Referring Image Matting](https://mlsanity.com/paper/2206.05149/) (2022)
- [Matting by Generation](https://mlsanity.com/paper/2407.21017/) (2024)
- [Deep Image Matting: A Comprehensive Survey](https://mlsanity.com/paper/2304.04672/) (2023)
- [From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction](https://mlsanity.com/paper/2602.01661/) (2026)
- [AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning](https://mlsanity.com/paper/2507.09308/) (2025)
- [Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner](https://mlsanity.com/paper/2509.24979/) (2025)
- [Adversarially-Guided Portrait Matting](https://mlsanity.com/paper/2305.02981/) (2023)
- [Training Matting Models without Alpha Labels](https://mlsanity.com/paper/2408.10539/) (2024)
- [SDMatte: Grafting Diffusion Models for Interactive Matting](https://mlsanity.com/paper/2508.00443/) (2025)
- [In-Context Matting](https://mlsanity.com/paper/2403.15789/) (2024)
- [Generative Video Matting](https://mlsanity.com/paper/2508.07905/) (2025)
- [Exploring the Interactive Guidance for Unified and Effective Image Matting](https://mlsanity.com/paper/2205.08324/) (2022)
- [OmniForce: On Human-Centered, Large Model Empowered and Cloud-Edge Collaborative AutoML System](https://mlsanity.com/paper/2303.00501/) (2023)
- [Zippo: Zipping Color and Transparency Distributions into a Single Diffusion Model](https://mlsanity.com/paper/2403.11077/) (2024)
- [DFIMat: Decoupled Flexible Interactive Matting in Multi-Person Scenarios](https://mlsanity.com/paper/2410.09788/) (2024)
- [Human-imperceptible, Machine-recognizable Images](https://mlsanity.com/paper/2306.03679/) (2023)
- [Efficient Portrait Matte Creation With Layer Diffusion and Connectivity Priors](https://mlsanity.com/paper/2501.16147/) (2025)
- [Enhancing Image Matting in Real-World Scenes with Mask-Guided Iterative Refinement](https://mlsanity.com/paper/2502.17093/) (2025)
- [From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models](https://mlsanity.com/paper/2607.06553/) (2026)
- [A Cost-Efficient Approach for Creating Virtual Fitting Room using Generative Adversarial Networks (GANs)](https://mlsanity.com/paper/2402.00994/) (2024)
- [DART: Depth-Enhanced Accurate and Real-Time Background Matting](https://mlsanity.com/paper/2402.15820/) (2024)
- [Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting](https://mlsanity.com/paper/2403.19213/) (2024)
- [D3-Predictor: Noise-Free Deterministic Diffusion for Dense Prediction](https://mlsanity.com/paper/2512.07062/) (2025)
- [Parallax Portrait Matting](https://mlsanity.com/paper/2607.11205/) (2026)

## Abstract (arXiv)

Recently, there has been an increasing concern about the privacy issue raised by identifiable information in machine learning. However, previous portrait matting methods were all based on identifiable images. To fill the gap, we present P3M-10k, which is the first large-scale anonymized benchmark for Privacy-Preserving Portrait Matting (P3M). P3M-10k consists of 10,421 high resolution face-blurred portrait images along with high-quality alpha mattes, which enables us to systematically evaluate both trimap-free and trimap-based matting methods and obtain some useful findings about model generalization ability under the privacy preserving training (PPT) setting. We also present a unified matting model dubbed P3M-Net that is compatible with both CNN and transformer backbones. To further mitigate the cross-domain performance gap issue under the PPT setting, we devise a simple yet effective Copy and Paste strategy (P3M-CP), which borrows facial information from public celebrity images and directs the network to reacquire the face context at both data and feature level. Extensive experiments on P3M-10k and public benchmarks demonstrate the superiority of P3M-Net over state-of-the-art methods and the effectiveness of P3M-CP in improving the cross-domain generalization ability, implying a great significance of P3M for future research and real-world applications.