# Dual-Hybrid Attention Network for Specular Highlight Removal

arXiv: https://arxiv.org/abs/2407.12255 · HTML: https://mlsanity.com/paper/2407.12255/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 8 references that are in the map.
- First posted on arXiv 17 Jul 2024.

## Builds on (most cited first, 2 of 2)

- [A Large-scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement](https://mlsanity.com/paper/2301.08880/) (2023)
- [WavEnhancer: Unifying Wavelet and Transformer for Image Enhancement](https://mlsanity.com/paper/2212.08327/) (2022)

## Built on by (most cited first, 18 of 18)

- [Image Fusion for Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2502.15694/) (2024)
- [Prompt Categories Cluster for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2412.13823/) (2024)
- [Image Augmentation Agent for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2412.20439/) (2024)
- [SMAFormer: Synergistic Multi-Attention Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2409.00346/) (2024)
- [Underwater Image Restoration via Polymorphic Large Kernel CNNs](https://mlsanity.com/paper/2412.18459/) (2024)
- [High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer](https://mlsanity.com/paper/2410.22922/) (2024)
- [Test-Time Intensity Consistency Adaptation for Shadow Detection](https://mlsanity.com/paper/2410.07695/) (2024)
- [LensNet: An End-to-End Learning Framework for Empirical Point Spread Function Modeling and Lensless Imaging Reconstruction](https://mlsanity.com/paper/2505.01755/) (2025)
- [UIE-UnFold: Deep Unfolding Network with Color Priors and Vision Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2408.10653/) (2024)
- [IMAN: An Adaptive Network for Robust NPC Mortality Prediction with Missing Modalities](https://mlsanity.com/paper/2410.18551/) (2024)
- [DLEN: Dual Branch of Transformer for Low-Light Image Enhancement in Dual Domains](https://mlsanity.com/paper/2501.12235/) (2025)
- [CubeRobot: Grounding Language in Rubik's Cube Manipulation via Vision-Language Model](https://mlsanity.com/paper/2503.19281/) (2025)
- [Contrastive Prompt Clustering for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2508.17009/) (2025)
- [UnReflectAnything: RGB-Only Highlight Removal by Rendering Synthetic Specular Supervision](https://mlsanity.com/paper/2512.09583/) (2025)
- [TAGE: Trustworthy Attribute Group Editing for Stable Few-shot Image Generation](https://mlsanity.com/paper/2410.17855/) (2024)
- [Single Document Image Highlight Removal via A Large-Scale Real-World Dataset and A Location-Aware Network](https://mlsanity.com/paper/2504.14238/) (2025)
- [Forestpest-YOLO: A High-Performance Detection Framework for Small Forestry Pests](https://mlsanity.com/paper/2510.00547/) (2025)
- [Shift-Window Meets Dual Attention: A Multi-Model Architecture for Specular Highlight Removal](https://mlsanity.com/paper/2512.04496/) (2025)

## Abstract (arXiv)

Specular highlight removal plays a pivotal role in multimedia applications, as it enhances the quality and interpretability of images and videos, ultimately improving the performance of downstream tasks such as content-based retrieval, object recognition, and scene understanding. Despite significant advances in deep learning-based methods, current state-of-the-art approaches often rely on additional priors or supervision, limiting their practicality and generalization capability. In this paper, we propose the Dual-Hybrid Attention Network for Specular Highlight Removal (DHAN-SHR), an end-to-end network that introduces novel hybrid attention mechanisms to effectively capture and process information across different scales and domains without relying on additional priors or supervision. DHAN-SHR consists of two key components: the Adaptive Local Hybrid-Domain Dual Attention Transformer (L-HD-DAT) and the Adaptive Global Dual Attention Transformer (G-DAT). The L-HD-DAT captures local inter-channel and inter-pixel dependencies while incorporating spectral domain features, enabling the network to effectively model the complex interactions between specular highlights and the underlying surface properties. The G-DAT models global inter-channel relationships and long-distance pixel dependencies, allowing the network to propagate contextual information across the entire image and generate more coherent and consistent highlight-free results. To evaluate the performance of DHAN-SHR and facilitate future research in this area, we compile a large-scale benchmark dataset comprising a diverse range of images with varying levels of specular highlights. Through extensive experiments, we demonstrate that DHAN-SHR outperforms 18 state-of-the-art methods both quantitatively and qualitatively, setting a new standard for specular highlight removal in multimedia applications.