# Deep Image Matting

arXiv: https://arxiv.org/abs/1703.03872 · HTML: https://mlsanity.com/paper/1703.03872/

## Key facts

- Cited by 150 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Mar 2017.

## Built on by (most cited first, 30 of 150)

- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Robust High-Resolution Video Matting with Temporal Guidance](https://mlsanity.com/paper/2108.11515/) (2021)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [Bilateral Reference for High-Resolution Dichotomous Image Segmentation](https://mlsanity.com/paper/2401.03407/) (2024)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [FocalClick: Towards Practical Interactive Image Segmentation](https://mlsanity.com/paper/2204.02574/) (2022)
- [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)
- [ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers](https://mlsanity.com/paper/2305.15272/) (2023)
- [Semantic Image Matting](https://mlsanity.com/paper/2104.08201/) (2021)
- [Omnimatte: Associating Objects and Their Effects in Video](https://mlsanity.com/paper/2105.06993/) (2021)
- [MatteFormer: Transformer-Based Image Matting via Prior-Tokens](https://mlsanity.com/paper/2203.15662/) (2022)
- [BokehMe: When Neural Rendering Meets Classical Rendering](https://mlsanity.com/paper/2206.12614/) (2022)
- [Boundary-Aware Segmentation Network for Mobile and Web Applications](https://mlsanity.com/paper/2101.04704/) (2021)
- [Deep Video Matting via Spatio-Temporal Alignment and Aggregation](https://mlsanity.com/paper/2104.11208/) (2021)
- [Matte Anything: Interactive Natural Image Matting with Segment Anything Models](https://mlsanity.com/paper/2306.04121/) (2023)
- [MULAN: A Multi Layer Annotated Dataset for Controllable Text-to-Image Generation](https://mlsanity.com/paper/2404.02790/) (2024)
- [Text2Layer: Layered Image Generation using Latent Diffusion Model](https://mlsanity.com/paper/2307.09781/) (2023)
- [ObjectStitch: Generative Object Compositing](https://mlsanity.com/paper/2212.00932/) (2022)
- [SOLO: A Simple Framework for Instance Segmentation](https://mlsanity.com/paper/2106.15947/) (2021)
- [A Unified Query-based Paradigm for Point Cloud Understanding](https://mlsanity.com/paper/2203.01252/) (2022)
- [SAPA: Similarity-Aware Point Affiliation for Feature Upsampling](https://mlsanity.com/paper/2209.12866/) (2022)
- [Matting Anything](https://mlsanity.com/paper/2306.05399/) (2023)
- [LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation](https://mlsanity.com/paper/2303.12343/) (2023)
- [Attention-guided Temporally Coherent Video Object Matting](https://mlsanity.com/paper/2105.11427/) (2021)
- [Rethinking Portrait Matting with Privacy Preserving](https://mlsanity.com/paper/2203.16828/) (2022)
- [Human Instance Matting via Mutual Guidance and Multi-Instance Refinement](https://mlsanity.com/paper/2205.10767/) (2022)
- [FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling](https://mlsanity.com/paper/2207.10392/) (2022)
- [PP-Matting: High-Accuracy Natural Image Matting](https://mlsanity.com/paper/2204.09433/) (2022)

## Abstract (arXiv)

Image matting is a fundamental computer vision problem and has many applications. Previous algorithms have poor performance when an image has similar foreground and background colors or complicated textures. The main reasons are prior methods 1) only use low-level features and 2) lack high-level context. In this paper, we propose a novel deep learning based algorithm that can tackle both these problems. Our deep model has two parts. The first part is a deep convolutional encoder-decoder network that takes an image and the corresponding trimap as inputs and predict the alpha matte of the image. The second part is a small convolutional network that refines the alpha matte predictions of the first network to have more accurate alpha values and sharper edges. In addition, we also create a large-scale image matting dataset including 49300 training images and 1000 testing images. We evaluate our algorithm on the image matting benchmark, our testing set, and a wide variety of real images. Experimental results clearly demonstrate the superiority of our algorithm over previous methods.