# Bridging Composite and Real: Towards End-to-end Deep Image Matting

arXiv: https://arxiv.org/abs/2010.16188 · HTML: https://mlsanity.com/paper/2010.16188/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Oct 2020.

## Built on by (most cited first, 30 of 89)

- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Bilateral Reference for High-Resolution Dichotomous Image Segmentation](https://mlsanity.com/paper/2401.03407/) (2024)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (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)
- [Text2Layer: Layered Image Generation using Latent Diffusion Model](https://mlsanity.com/paper/2307.09781/) (2023)
- [Matting Anything](https://mlsanity.com/paper/2306.05399/) (2023)
- [Rethinking Portrait Matting with Privacy Preserving](https://mlsanity.com/paper/2203.16828/) (2022)
- [PP-Matting: High-Accuracy Natural Image Matting](https://mlsanity.com/paper/2204.09433/) (2022)
- [Referring Image Matting](https://mlsanity.com/paper/2206.05149/) (2022)
- [Generating Images with 3D Annotations Using Diffusion Models](https://mlsanity.com/paper/2306.08103/) (2023)
- [MaGGIe: Masked Guided Gradual Human Instance Matting](https://mlsanity.com/paper/2404.16035/) (2024)
- [ZIM: Zero-Shot Image Matting for Anything](https://mlsanity.com/paper/2411.00626/) (2024)
- [The Robustness Limits of SoTA Vision Models to Natural Variation](https://mlsanity.com/paper/2210.13604/) (2022)
- [PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs](https://mlsanity.com/paper/2402.08657/) (2024)
- [Generating Compositional Scenes via Text-to-image RGBA Instance Generation](https://mlsanity.com/paper/2411.10913/) (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)
- [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)
- [Deep Image Matting: A Comprehensive Survey](https://mlsanity.com/paper/2304.04672/) (2023)
- [On the representation and methodology for wide and short range head pose estimation](https://mlsanity.com/paper/2401.05807/) (2024)
- [PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment](https://mlsanity.com/paper/2505.11468/) (2025)
- [Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences](https://mlsanity.com/paper/2406.10427/) (2024)
- [AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning](https://mlsanity.com/paper/2507.09308/) (2025)
- [VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement](https://mlsanity.com/paper/2312.04885/) (2023)
- [Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner](https://mlsanity.com/paper/2509.24979/) (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)

## Abstract (arXiv)

Extracting accurate foregrounds from natural images benefits many downstream applications such as film production and augmented reality. However, the furry characteristics and various appearance of the foregrounds, e.g., animal and portrait, challenge existing matting methods, which usually require extra user inputs such as trimap or scribbles. To resolve these problems, we study the distinct roles of semantics and details for image matting and decompose the task into two parallel sub-tasks: high-level semantic segmentation and low-level details matting. Specifically, we propose a novel Glance and Focus Matting network (GFM), which employs a shared encoder and two separate decoders to learn both tasks in a collaborative manner for end-to-end natural image matting. Besides, due to the limitation of available natural images in the matting task, previous methods typically adopt composite images for training and evaluation, which result in limited generalization ability on real-world images. In this paper, we investigate the domain gap issue between composite images and real-world images systematically by conducting comprehensive analyses of various discrepancies between the foreground and background images. We find that a carefully designed composition route RSSN that aims to reduce the discrepancies can lead to a better model with remarkable generalization ability. Furthermore, we provide a benchmark containing 2,000 high-resolution real-world animal images and 10,000 portrait images along with their manually labeled alpha mattes to serve as a test bed for evaluating matting model's generalization ability on real-world images. Comprehensive empirical studies have demonstrated that GFM outperforms state-of-the-art methods and effectively reduces the generalization error. The code and the datasets will be released at https://github.com/JizhiziLi/GFM.