# Shift-Window Meets Dual Attention: A Multi-Model Architecture for Specular Highlight Removal

arXiv: https://arxiv.org/abs/2512.04496 · HTML: https://mlsanity.com/paper/2512.04496/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 41 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation](https://mlsanity.com/paper/2405.06880/) (2024)
- [Poly Kernel Inception Network for Remote Sensing Detection](https://mlsanity.com/paper/2403.06258/) (2024)
- [Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning](https://mlsanity.com/paper/2211.14751/) (2022)
- [Dual-Hybrid Attention Network for Specular Highlight Removal](https://mlsanity.com/paper/2407.12255/) (2024)
- [Polarization Guided Specular Reflection Separation](https://mlsanity.com/paper/2103.11652/) (2021)
- [Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data](https://mlsanity.com/paper/2309.06302/) (2023)

## Abstract (arXiv)

Inevitable specular highlights in practical environments severely impair the visual performance, thus degrading the task effectiveness and efficiency. Although there exist considerable methods that focus on local information from convolutional neural network models or global information from transformer models, the single-type model falls into a modeling dilemma between local fine-grained details and global long-range dependencies, thus deteriorating for specular highlights with different scales. Therefore, to accommodate specular highlights of all scales, we propose a multi-model architecture for specular highlight removal (MM-SHR) that effectively captures fine-grained features in highlight regions and models long-range dependencies between highlight and highlight-free areas. Specifically, we employ convolution operations to extract local details in the shallow layers of MM-SHR, and utilize the attention mechanism to capture global features in the deep layers, ensuring both operation efficiency and removal accuracy. To model long-range dependencies without compromising computational complexity, we utilize a coarse-to-fine manner and propose Omni-Directional Attention Integration Block(OAIBlock) and Adaptive Region-Aware Hybrid-Domain Dual Attention Convolutional Network(HDDAConv) , which leverage omni-directiona pixel-shifting and window-dividing operations at the raw features to achieve specular highlight removal. Extensive experimental results on three benchmark tasks and six types of surface materials demonstrate that MM-SHR outperforms state-of-the-art methods in both accuracy and efficiency for specular highlight removal. The implementation will be made publicly available at https://github.com/Htcicv/MM-SHR.