# Prior-Induced Information Alignment for Image Matting

arXiv: https://arxiv.org/abs/2106.14439 · HTML: https://mlsanity.com/paper/2106.14439/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 28 Jun 2021.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [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)
- [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)
- [Boosting Semantic Human Matting with Coarse Annotations](https://mlsanity.com/paper/2004.04955/) (2020)
- [Disentangled Image Matting](https://mlsanity.com/paper/1909.04686/) (2019)
- [Deep Residual Learning in the JPEG Transform Domain](https://mlsanity.com/paper/1812.11690/) (2018)
- [DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors](https://mlsanity.com/paper/1908.08837/) (2019)
- [Smart Scribbles for Image Mating](https://mlsanity.com/paper/2103.17062/) (2021)
- [Multi-scale Information Assembly for Image Matting](https://mlsanity.com/paper/2101.02391/) (2021)
- [Learning Transparent Object Matting](https://mlsanity.com/paper/1907.11544/) (2019)

## Built on by (most cited first, 6 of 6)

- [Progressive Glass Segmentation](https://mlsanity.com/paper/2209.02280/) (2022)
- [Large-Field Contextual Feature Learning for Glass Detection](https://mlsanity.com/paper/2209.04639/) (2022)
- [Zero-Shot Image Harmonization with Generative Model Prior](https://mlsanity.com/paper/2307.08182/) (2023)
- [Trimap-guided Feature Mining and Fusion Network for Natural Image Matting](https://mlsanity.com/paper/2112.00510/) (2021)
- [Exploring the Interactive Guidance for Unified and Effective Image Matting](https://mlsanity.com/paper/2205.08324/) (2022)
- [Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting](https://mlsanity.com/paper/2403.19213/) (2024)

## Abstract (arXiv)

Image matting is an ill-posed problem that aims to estimate the opacity of foreground pixels in an image. However, most existing deep learning-based methods still suffer from the coarse-grained details. In general, these algorithms are incapable of felicitously distinguishing the degree of exploration between deterministic domains (certain FG and BG pixels) and undetermined domains (uncertain in-between pixels), or inevitably lose information in the continuous sampling process, leading to a sub-optimal result. In this paper, we propose a novel network named Prior-Induced Information Alignment Matting Network (PIIAMatting), which can efficiently model the distinction of pixel-wise response maps and the correlation of layer-wise feature maps. It mainly consists of a Dynamic Gaussian Modulation mechanism (DGM) and an Information Alignment strategy (IA). Specifically, the DGM can dynamically acquire a pixel-wise domain response map learned from the prior distribution. The response map can present the relationship between the opacity variation and the convergence process during training. On the other hand, the IA comprises an Information Match Module (IMM) and an Information Aggregation Module (IAM), jointly scheduled to match and aggregate the adjacent layer-wise features adaptively. Besides, we also develop a Multi-Scale Refinement (MSR) module to integrate multi-scale receptive field information at the refinement stage to recover the fluctuating appearance details. Extensive quantitative and qualitative evaluations demonstrate that the proposed PIIAMatting performs favourably against state-of-the-art image matting methods on the Alphamatting.com, Composition-1K and Distinctions-646 dataset.