# PP-Matting: High-Accuracy Natural Image Matting

arXiv: https://arxiv.org/abs/2204.09433 · HTML: https://mlsanity.com/paper/2204.09433/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 20 Apr 2022.

## Builds on (most cited first, 23 of 23)

- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Real-Time High-Resolution Background Matting](https://mlsanity.com/paper/2012.07810/) (2020)
- [Gated-SCNN: Gated Shape CNNs for Semantic Segmentation](https://mlsanity.com/paper/1907.05740/) (2019)
- [Deep Image Matting](https://mlsanity.com/paper/1703.03872/) (2017)
- [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)
- [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)
- [Semantic Human Matting](https://mlsanity.com/paper/1809.01354/) (2018)
- [Information-Flow Matting](https://mlsanity.com/paper/1707.05055/) (2017)
- [Deep Automatic Natural Image Matting](https://mlsanity.com/paper/2107.07235/) (2021)
- [Semantic Image Matting](https://mlsanity.com/paper/2104.08201/) (2021)
- [AlphaGAN: Generative adversarial networks for natural image matting](https://mlsanity.com/paper/1807.10088/) (2018)
- [Boosting Semantic Human Matting with Coarse Annotations](https://mlsanity.com/paper/2004.04955/) (2020)
- [Disentangled Image Matting](https://mlsanity.com/paper/1909.04686/) (2019)
- [High-Resolution Deep Image Matting](https://mlsanity.com/paper/2009.06613/) (2020)
- [PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation](https://mlsanity.com/paper/2101.06175/) (2021)
- [Cascade Image Matting with Deformable Graph Refinement](https://mlsanity.com/paper/2105.02646/) (2021)
- [PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset](https://mlsanity.com/paper/2112.07146/) (2021)
- [Salient Image Matting](https://mlsanity.com/paper/2103.12337/) (2021)
- [AlphaNet: An Attention Guided Deep Network for Automatic Image Matting](https://mlsanity.com/paper/2003.03613/) (2020)

## Built on by (most cited first, 23 of 23)

- [ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generation](https://mlsanity.com/paper/2302.13848/) (2023)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [TransAnimate: Taming Layer Diffusion to Generate RGBA Video](https://mlsanity.com/paper/2503.17934/) (2025)
- [LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors](https://mlsanity.com/paper/2412.04460/) (2024)
- [MaGGIe: Masked Guided Gradual Human Instance Matting](https://mlsanity.com/paper/2404.16035/) (2024)
- [EmoTalk3D: High-Fidelity Free-View Synthesis of Emotional 3D Talking Head](https://mlsanity.com/paper/2408.00297/) (2024)
- [OmniPSD: Layered PSD Generation with Diffusion Transformer](https://mlsanity.com/paper/2512.09247/) (2025)
- [Robust Human Matting via Semantic Guidance](https://mlsanity.com/paper/2210.05210/) (2022)
- [TransPixeler: Advancing Text-to-Video Generation with Transparency](https://mlsanity.com/paper/2501.03006/) (2025)
- [PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment](https://mlsanity.com/paper/2505.11468/) (2025)
- [EISeg: An Efficient Interactive Segmentation Tool based on PaddlePaddle](https://mlsanity.com/paper/2210.08788/) (2022)
- [Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation](https://mlsanity.com/paper/2309.05956/) (2023)
- [GRAPE: Generalizable and Robust Multi-view Facial Capture](https://mlsanity.com/paper/2407.10193/) (2024)
- [Virtual Occlusions Through Implicit Depth](https://mlsanity.com/paper/2305.07014/) (2023)
- [High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field](https://mlsanity.com/paper/2310.06275/) (2023)
- [HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion](https://mlsanity.com/paper/2512.14542/) (2025)
- [Video Instance Matting](https://mlsanity.com/paper/2311.04212/) (2023)
- [SDMatte: Grafting Diffusion Models for Interactive Matting](https://mlsanity.com/paper/2508.00443/) (2025)
- [TransVDM: Motion-Constrained Video Diffusion Model for Transparent Video Synthesis](https://mlsanity.com/paper/2502.19454/) (2025)
- [3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography](https://mlsanity.com/paper/2210.05104/) (2022)
- [3D Matting: A Soft Segmentation Method Applied in Computed Tomography](https://mlsanity.com/paper/2209.07843/) (2022)
- [POBEVM: Real-time Video Matting via Progressively Optimize the Target Body and Edge](https://mlsanity.com/paper/2402.09731/) (2024)
- [Uncertainty-Guided Face Matting for Occlusion-Aware Face Transformation](https://mlsanity.com/paper/2508.03055/) (2025)

## Abstract (arXiv)

Natural image matting is a fundamental and challenging computer vision task. It has many applications in image editing and composition. Recently, deep learning-based approaches have achieved great improvements in image matting. However, most of them require a user-supplied trimap as an auxiliary input, which limits the matting applications in the real world. Although some trimap-free approaches have been proposed, the matting quality is still unsatisfactory compared to trimap-based ones. Without the trimap guidance, the matting models suffer from foreground-background ambiguity easily, and also generate blurry details in the transition area. In this work, we propose PP-Matting, a trimap-free architecture that can achieve high-accuracy natural image matting. Our method applies a high-resolution detail branch (HRDB) that extracts fine-grained details of the foreground with keeping feature resolution unchanged. Also, we propose a semantic context branch (SCB) that adopts a semantic segmentation subtask. It prevents the detail prediction from local ambiguity caused by semantic context missing. In addition, we conduct extensive experiments on two well-known benchmarks: Composition-1k and Distinctions-646. The results demonstrate the superiority of PP-Matting over previous methods. Furthermore, we provide a qualitative evaluation of our method on human matting which shows its outstanding performance in the practical application. The code and pre-trained models will be available at PaddleSeg: https://github.com/PaddlePaddle/PaddleSeg.