# Deep Multi-class Adversarial Specularity Removal

arXiv: https://arxiv.org/abs/1904.02672 · HTML: https://mlsanity.com/paper/1904.02672/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

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

- [Text-Aware Single Image Specular Highlight Removal](https://mlsanity.com/paper/2108.06881/) (2021)
- [LIGHTS: LIGHT Specularity Dataset for specular detection in Multi-view](https://mlsanity.com/paper/2101.10772/) (2021)
- [A Multiple-View Geometric Model for Specularity Prediction on General Curved Surfaces](https://mlsanity.com/paper/2108.09378/) (2021)
- [M2-Net: Multi-stages Specular Highlight Detection and Removal in Multi-scenes](https://mlsanity.com/paper/2207.09965/) (2022)

## Abstract (arXiv)

We propose a novel learning approach, in the form of a fully-convolutional neural network (CNN), which automatically and consistently removes specular highlights from a single image by generating its diffuse component. To train the generative network, we define an adversarial loss on a discriminative network as in the GAN framework and combined it with a content loss. In contrast to existing GAN approaches, we implemented the discriminator to be a multi-class classifier instead of a binary one, to find more constraining features. This helps the network pinpoint the diffuse manifold by providing two more gradient terms. We also rendered a synthetic dataset designed to help the network generalize well. We show that our model performs well across various synthetic and real images and outperforms the state-of-the-art in consistency.