# F, B, Alpha Matting

arXiv: https://arxiv.org/abs/2003.07711 · HTML: https://mlsanity.com/paper/2003.07711/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2020.

## Built on by (most cited first, 30 of 50)

- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [Robust High-Resolution Video Matting with Temporal Guidance](https://mlsanity.com/paper/2108.11515/) (2021)
- [Privacy-Preserving Portrait Matting](https://mlsanity.com/paper/2104.14222/) (2021)
- [SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting](https://mlsanity.com/paper/2109.01068/) (2021)
- [Matte Anything: Interactive Natural Image Matting with Segment Anything Models](https://mlsanity.com/paper/2306.04121/) (2023)
- [A Unified Query-based Paradigm for Point Cloud Understanding](https://mlsanity.com/paper/2203.01252/) (2022)
- [Matting Anything](https://mlsanity.com/paper/2306.05399/) (2023)
- [Rethinking Portrait Matting with Privacy Preserving](https://mlsanity.com/paper/2203.16828/) (2022)
- [Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation](https://mlsanity.com/paper/2201.06889/) (2022)
- [VMFormer: End-to-End Video Matting with Transformer](https://mlsanity.com/paper/2208.12801/) (2022)
- [MaGGIe: Masked Guided Gradual Human Instance Matting](https://mlsanity.com/paper/2404.16035/) (2024)
- [Convolutional Neural Opacity Radiance Fields](https://mlsanity.com/paper/2104.01772/) (2021)
- [TransMatting: Enhancing Transparent Objects Matting with Transformers](https://mlsanity.com/paper/2208.03007/) (2022)
- [One-Trimap Video Matting](https://mlsanity.com/paper/2207.13353/) (2022)
- [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)
- [Cascade Image Matting with Deformable Graph Refinement](https://mlsanity.com/paper/2105.02646/) (2021)
- [Diffusion for Natural Image Matting](https://mlsanity.com/paper/2312.05915/) (2023)
- [FactorMatte: Redefining Video Matting for Re-Composition Tasks](https://mlsanity.com/paper/2211.02145/) (2022)
- [Adaptive Human Matting for Dynamic Videos](https://mlsanity.com/paper/2304.06018/) (2023)
- [Lightweight Portrait Matting via Regional Attention and Refinement](https://mlsanity.com/paper/2311.03770/) (2023)
- [Video Instance Matting](https://mlsanity.com/paper/2311.04212/) (2023)
- [End-to-End Human Instance Matting](https://mlsanity.com/paper/2403.01510/) (2024)
- [SDMatte: Grafting Diffusion Models for Interactive Matting](https://mlsanity.com/paper/2508.00443/) (2025)
- [Alpha Matte Generation from Single Input for Portrait Matting](https://mlsanity.com/paper/2106.03210/) (2021)
- [Generalizing Interactive Backpropagating Refinement for Dense Prediction](https://mlsanity.com/paper/2112.10969/) (2021)
- [Imitrob: Imitation Learning Dataset for Training and Evaluating 6D Object Pose Estimators](https://mlsanity.com/paper/2209.07976/) (2022)
- [Learning Trimaps via Clicks for Image Matting](https://mlsanity.com/paper/2404.00335/) (2024)
- [Towards Label-Efficient Human Matting: A Simple Baseline for Weakly Semi-Supervised Trimap-Free Human Matting](https://mlsanity.com/paper/2404.00921/) (2024)
- [Trimap-guided Feature Mining and Fusion Network for Natural Image Matting](https://mlsanity.com/paper/2112.00510/) (2021)

## Abstract (arXiv)

Cutting out an object and estimating its opacity mask, known as image matting, is a key task in many image editing applications. Deep learning approaches have made significant progress by adapting the encoder-decoder architecture of segmentation networks. However, most of the existing networks only predict the alpha matte and post-processing methods must then be used to recover the original foreground and background colours in the transparent regions. Recently, two methods have shown improved results by also estimating the foreground colours, but at a significant computational and memory cost. In this paper, we propose a low-cost modification to alpha matting networks to also predict the foreground and background colours. We study variations of the training regime and explore a wide range of existing and novel loss functions for the joint prediction. Our method achieves the state of the art performance on the Adobe Composition-1k dataset for alpha matte and composite colour quality. It is also the current best performing method on the alphamatting.com online evaluation.