# M2-Net: Multi-stages Specular Highlight Detection and Removal in Multi-scenes

arXiv: https://arxiv.org/abs/2207.09965 · HTML: https://mlsanity.com/paper/2207.09965/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 44 references that are in the map.
- First posted on arXiv 20 Jul 2022.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting](https://mlsanity.com/paper/2005.09704/) (2020)
- [Cascaded Refinement Network for Point Cloud Completion](https://mlsanity.com/paper/2004.03327/) (2020)
- [Decoupled Attention Network for Text Recognition](https://mlsanity.com/paper/1912.10205/) (2019)
- [Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN](https://mlsanity.com/paper/1904.10247/) (2019)
- [Contextual-based Image Inpainting: Infer, Match, and Translate](https://mlsanity.com/paper/1711.08590/) (2017)
- [CANet: A Context-Aware Network for Shadow Removal](https://mlsanity.com/paper/2108.09894/) (2021)
- [A Dataset of Multi-Illumination Images in the Wild](https://mlsanity.com/paper/1910.08131/) (2019)
- [Robust Reflection Removal with Reflection-free Flash-only Cues](https://mlsanity.com/paper/2103.04273/) (2021)
- [Deep Multi-class Adversarial Specularity Removal](https://mlsanity.com/paper/1904.02672/) (2019)
- [Text-Aware Single Image Specular Highlight Removal](https://mlsanity.com/paper/2108.06881/) (2021)

## Abstract (arXiv)

In this paper, we propose a novel uniformity framework for highlight detection and removal in multi-scenes, including synthetic images, face images, natural images, and text images. The framework consists of three main components, highlight feature extractor module, highlight coarse removal module, and highlight refine removal module. Firstly, the highlight feature extractor module can directly separate the highlight feature and non-highlight feature from the original highlight image. Then highlight removal image is obtained using a coarse highlight removal network. To further improve the highlight removal effect, the refined highlight removal image is finally obtained using refine highlight removal module based on contextual highlight attention mechanisms. Extensive experimental results in multiple scenes indicate that the proposed framework can obtain excellent visual effects of highlight removal and achieve state-of-the-art results in several quantitative evaluation metrics. Our algorithm is applied for the first time in video highlight removal with promising results.