# ShadowFormer: Global Context Helps Image Shadow Removal

arXiv: https://arxiv.org/abs/2302.01650 · HTML: https://mlsanity.com/paper/2302.01650/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 49 references that are in the map.
- First posted on arXiv 3 Feb 2023.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN](https://mlsanity.com/paper/1911.08718/) (2019)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [Shadow Removal via Shadow Image Decomposition](https://mlsanity.com/paper/1908.08628/) (2019)
- [Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data](https://mlsanity.com/paper/1903.10683/) (2019)
- [Auto-Exposure Fusion for Single-Image Shadow Removal](https://mlsanity.com/paper/2103.01255/) (2021)
- [DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network](https://mlsanity.com/paper/2207.10434/) (2022)
- [Direction-aware Spatial Context Features for Shadow Detection and Removal](https://mlsanity.com/paper/1805.04635/) (2018)
- [ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal](https://mlsanity.com/paper/1908.01323/) (2019)
- [Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyond](https://mlsanity.com/paper/2203.16931/) (2022)
- [CANet: A Context-Aware Network for Shadow Removal](https://mlsanity.com/paper/2108.09894/) (2021)
- [Improving Shadow Suppression for Illumination Robust Face Recognition](https://mlsanity.com/paper/1710.05073/) (2017)
- [Context-Transformer: Tackling Object Confusion for Few-Shot Detection](https://mlsanity.com/paper/2003.07304/) (2020)
- [Learning from Synthetic Shadows for Shadow Detection and Removal](https://mlsanity.com/paper/2101.01713/) (2021)
- [ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2107.05830/) (2021)
- [Conditional GANs for Multi-Illuminant Color Constancy: Revolution or Yet Another Approach?](https://mlsanity.com/paper/1811.06604/) (2018)
- [Exploiting Non-Local Priors via Self-Convolution For Highly-Efficient Image Restoration](https://mlsanity.com/paper/2006.13714/) (2020)
- [Enhancing Low-Light Images in Real World via Cross-Image Disentanglement](https://mlsanity.com/paper/2201.03145/) (2022)

## Built on by (most cited first, 30 of 35)

- [Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation](https://mlsanity.com/paper/2406.11824/) (2024)
- [Backdoor Attacks Against Deep Image Compression via Adaptive Frequency Trigger](https://mlsanity.com/paper/2302.14677/) (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)
- [Latent Feature-Guided Diffusion Models for Shadow Removal](https://mlsanity.com/paper/2312.02156/) (2023)
- [UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video](https://mlsanity.com/paper/2306.09349/) (2023)
- [ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer](https://mlsanity.com/paper/2406.02559/) (2024)
- [OmniSR: Shadow Removal under Direct and Indirect Lighting](https://mlsanity.com/paper/2410.01719/) (2024)
- [Shadow Generation for Composite Image Using Diffusion model](https://mlsanity.com/paper/2403.15234/) (2024)
- [Detail-Preserving Latent Diffusion for Stable Shadow Removal](https://mlsanity.com/paper/2412.17630/) (2024)
- [Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks](https://mlsanity.com/paper/2403.10076/) (2024)
- [Diff-Shadow: Global-guided Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2407.16214/) (2024)
- [DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal](https://mlsanity.com/paper/2307.15318/) (2023)
- [Towards Image Ambient Lighting Normalization](https://mlsanity.com/paper/2403.18730/) (2024)
- [Adaptive Window Pruning for Efficient Local Motion Deblurring](https://mlsanity.com/paper/2306.14268/) (2023)
- [S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal](https://mlsanity.com/paper/2404.12103/) (2024)
- [Shadow Removal Refinement via Material-Consistent Shadow Edges](https://mlsanity.com/paper/2409.06848/) (2024)
- [MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis](https://mlsanity.com/paper/2412.02635/) (2024)
- [DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation](https://mlsanity.com/paper/2308.09972/) (2023)
- [Progressive Recurrent Network for Shadow Removal](https://mlsanity.com/paper/2311.00455/) (2023)
- [Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal](https://mlsanity.com/paper/2309.11715/) (2023)
- [ShadowSense: Unsupervised Domain Adaptation and Feature Fusion for Shadow-Agnostic Tree Crown Detection from RGB-Thermal Drone Imagery](https://mlsanity.com/paper/2310.16212/) (2023)
- [Prompt-Aware Controllable Shadow Removal](https://mlsanity.com/paper/2501.15043/) (2025)
- [Unsupervised Deep Digital Staining For Microscopic Cell Images Via Knowledge Distillation](https://mlsanity.com/paper/2303.02057/) (2023)
- [Camera Relocalization in Shadow-free Neural Radiance Fields](https://mlsanity.com/paper/2405.14824/) (2024)
- [Leveraging Contrast Information for Efficient Document Shadow Removal](https://mlsanity.com/paper/2504.00385/) (2025)
- [NTIRE 2025 Image Shadow Removal Challenge Report](https://mlsanity.com/paper/2506.15524/) (2025)
- [NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI](https://mlsanity.com/paper/2403.08995/) (2024)
- [Accurate Tennis Court Line Detection on Amateur Recorded Matches](https://mlsanity.com/paper/2404.06977/) (2024)
- [Soft-Hard Attention U-Net Model and Benchmark Dataset for Multiscale Image Shadow Removal](https://mlsanity.com/paper/2408.03734/) (2024)
- [Elucidating the Design Space of Arbitrary-Noise-Based Diffusion Models](https://mlsanity.com/paper/2507.18534/) (2025)

## Abstract (arXiv)

Recent deep learning methods have achieved promising results in image shadow removal. However, most of the existing approaches focus on working locally within shadow and non-shadow regions, resulting in severe artifacts around the shadow boundaries as well as inconsistent illumination between shadow and non-shadow regions. It is still challenging for the deep shadow removal model to exploit the global contextual correlation between shadow and non-shadow regions. In this work, we first propose a Retinex-based shadow model, from which we derive a novel transformer-based network, dubbed ShandowFormer, to exploit non-shadow regions to help shadow region restoration. A multi-scale channel attention framework is employed to hierarchically capture the global information. Based on that, we propose a Shadow-Interaction Module (SIM) with Shadow-Interaction Attention (SIA) in the bottleneck stage to effectively model the context correlation between shadow and non-shadow regions. We conduct extensive experiments on three popular public datasets, including ISTD, ISTD+, and SRD, to evaluate the proposed method. Our method achieves state-of-the-art performance by using up to 150X fewer model parameters.