# Multi-scale Information Assembly for Image Matting

arXiv: https://arxiv.org/abs/2101.02391 · HTML: https://mlsanity.com/paper/2101.02391/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 54 references that are in the map.
- First posted on arXiv 7 Jan 2021.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [ParseNet: Looking Wider to See Better](https://mlsanity.com/paper/1506.04579/) (2015)
- [Deep Image Matting](https://mlsanity.com/paper/1703.03872/) (2017)
- [Pyramid Feature Attention Network for Saliency detection](https://mlsanity.com/paper/1903.00179/) (2019)
- [Indices Matter: Learning to Index for Deep Image Matting](https://mlsanity.com/paper/1908.00672/) (2019)
- [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)
- [AlphaGAN: Generative adversarial networks for natural image matting](https://mlsanity.com/paper/1807.10088/) (2018)
- [Disentangled Image Matting](https://mlsanity.com/paper/1909.04686/) (2019)
- [CRRN: Multi-Scale Guided Concurrent Reflection Removal Network](https://mlsanity.com/paper/1805.11802/) (2018)

## Built on by (most cited first, 10 of 10)

- [A Two-Stage Attentive Network for Single Image Super-Resolution](https://mlsanity.com/paper/2104.10488/) (2021)
- [TransMatting: Enhancing Transparent Objects Matting with Transformers](https://mlsanity.com/paper/2208.03007/) (2022)
- [Deep Image Matting: A Comprehensive Survey](https://mlsanity.com/paper/2304.04672/) (2023)
- [Progressive Glass Segmentation](https://mlsanity.com/paper/2209.02280/) (2022)
- [Prior-Induced Information Alignment for Image Matting](https://mlsanity.com/paper/2106.14439/) (2021)
- [Multi-domain Collaborative Feature Representation for Robust Visual Object Tracking](https://mlsanity.com/paper/2108.04521/) (2021)
- [CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2112.05975/) (2021)
- [Hierarchical and Progressive Image Matting](https://mlsanity.com/paper/2210.06906/) (2022)
- [TransMatting: Tri-token Equipped Transformer Model for Image Matting](https://mlsanity.com/paper/2303.06476/) (2023)
- [Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting](https://mlsanity.com/paper/2210.06919/) (2022)

## Abstract (arXiv)

Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images. We argue that the foreground objects can be represented by different-level information, including the central bodies, large-grained boundaries, refined details, etc. Based on this observation, in this paper, we propose a multi-scale information assembly framework (MSIA-matte) to pull out high-quality alpha mattes from single RGB images. Technically speaking, given an input image, we extract advanced semantics as our subject content and retain initial CNN features to encode different-level foreground expression, then combine them by our well-designed information assembly strategy. Extensive experiments can prove the effectiveness of the proposed MSIA-matte, and we can achieve state-of-the-art performance compared to most existing matting networks.