# Retinex-guided Histogram Transformer for Mask-free Shadow Removal

arXiv: https://arxiv.org/abs/2504.14092 · HTML: https://mlsanity.com/paper/2504.14092/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 15 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN](https://mlsanity.com/paper/1911.08718/) (2019)
- [Recasting Regional Lighting for Shadow Removal](https://mlsanity.com/paper/2402.00341/) (2024)
- [ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction](https://mlsanity.com/paper/2410.21535/) (2024)
- [Shadow-Aware Dynamic Convolution for Shadow Removal](https://mlsanity.com/paper/2205.04908/) (2022)

## Built on by (most cited first, 4 of 4)

- [PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors](https://mlsanity.com/paper/2601.17470/) (2026)
- [HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing](https://mlsanity.com/paper/2604.03800/) (2026)
- [UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization](https://mlsanity.com/paper/2604.13383/) (2026)
- [CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement](https://mlsanity.com/paper/2604.18032/) (2026)

## Abstract (arXiv)

While deep learning methods have achieved notable progress in shadow removal, many existing approaches rely on shadow masks that are difficult to obtain, limiting their generalization to real-world scenes. In this work, we propose ReHiT, an efficient mask-free shadow removal framework based on a hybrid CNN-Transformer architecture guided by Retinex theory. We first introduce a dual-branch pipeline to separately model reflectance and illumination components, and each is restored by our developed Illumination-Guided Hybrid CNN-Transformer (IG-HCT) module. Second, besides the CNN-based blocks that are capable of learning residual dense features and performing multi-scale semantic fusion, multi-scale semantic fusion, we develop the Illumination-Guided Histogram Transformer Block (IGHB) to effectively handle non-uniform illumination and spatially complex shadows. Extensive experiments on several benchmark datasets validate the effectiveness of our approach over existing mask-free methods. Trained solely on the NTIRE 2025 Shadow Removal Challenge dataset, our solution delivers competitive results with one of the smallest parameter sizes and fastest inference speeds among top-ranked entries, highlighting its applicability for real-world applications with limited computational resources. The code is available at https://github.com/dongw22/oath.