# MatteViT: High-Frequency-Aware Document Shadow Removal with Shadow Matte Guidance

arXiv: https://arxiv.org/abs/2512.08789 · HTML: https://mlsanity.com/paper/2512.08789/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data](https://mlsanity.com/paper/1903.10683/) (2019)
- [From Shadow Segmentation to Shadow Removal](https://mlsanity.com/paper/2008.00267/) (2020)
- [DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction](https://mlsanity.com/paper/2110.12942/) (2021)
- [Shadow Removal by a Lightness-Guided Network with Training on Unpaired Data](https://mlsanity.com/paper/2006.15617/) (2020)
- [DocDiff: Document Enhancement via Residual Diffusion Models](https://mlsanity.com/paper/2305.03892/) (2023)
- [High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net](https://mlsanity.com/paper/2308.14221/) (2023)
- [DocEnTr: An End-to-End Document Image Enhancement Transformer](https://mlsanity.com/paper/2201.10252/) (2022)
- [Water-Filling: An Efficient Algorithm for Digitized Document Shadow Removal](https://mlsanity.com/paper/1904.09763/) (2019)
- [ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removal](https://mlsanity.com/paper/2211.16675/) (2022)
- [UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior](https://mlsanity.com/paper/2210.08216/) (2022)
- [DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal](https://mlsanity.com/paper/2307.15318/) (2023)
- [A Survey on Deep learning based Document Image Enhancement](https://mlsanity.com/paper/2112.02719/) (2021)
- [LP-IOANet: Efficient High Resolution Document Shadow Removal](https://mlsanity.com/paper/2303.12862/) (2023)
- [Cascaded Detail-Preserving Networks for Super-Resolution of Document Images](https://mlsanity.com/paper/1911.10714/) (2019)
- [SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal](https://mlsanity.com/paper/2409.07041/) (2024)
- [ShaDocFormer: A Shadow-Attentive Threshold Detector With Cascaded Fusion Refiner for Document Shadow Removal](https://mlsanity.com/paper/2309.06670/) (2023)
- [Leveraging Contrast Information for Efficient Document Shadow Removal](https://mlsanity.com/paper/2504.00385/) (2025)

## Abstract (arXiv)

Document shadow removal is essential for enhancing the clarity of digitized documents. Preserving high-frequency details (e.g., text edges and lines) is critical in this process because shadows often obscure or distort fine structures. This paper proposes a matte vision transformer (MatteViT), a novel shadow removal framework that applies spatial and frequency-domain information to eliminate shadows while preserving fine-grained structural details. To effectively retain these details, we employ two preservation strategies. First, our method introduces a lightweight high-frequency amplification module (HFAM) that decomposes and adaptively amplifies high-frequency components. Second, we present a continuous luminance-based shadow matte, generated using a custom-built matte dataset and shadow matte generator, which provides precise spatial guidance from the earliest processing stage. These strategies enable the model to accurately identify fine-grained regions and restore them with high fidelity. Extensive experiments on public benchmarks (RDD and Kligler) demonstrate that MatteViT achieves state-of-the-art performance, providing a robust and practical solution for real-world document shadow removal. Furthermore, the proposed method better preserves text-level details in downstream tasks, such as optical character recognition, improving recognition performance over prior methods.