# SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network

arXiv: https://arxiv.org/abs/2011.11377 · HTML: https://mlsanity.com/paper/2011.11377/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

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

- [VCGAN: Video Colorization with Hybrid Generative Adversarial Network](https://mlsanity.com/paper/2104.12357/) (2021)
- [Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation](https://mlsanity.com/paper/2112.08913/) (2021)
- [Panoptic-aware Image-to-Image Translation](https://mlsanity.com/paper/2112.01926/) (2021)
- [SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation](https://mlsanity.com/paper/2303.11591/) (2023)
- [SPColor: Semantic Prior Guided Exemplar-based Image Colorization](https://mlsanity.com/paper/2304.06255/) (2023)
- [EvoMakeup: High-Fidelity and Controllable Makeup Editing with MakeupQuad](https://mlsanity.com/paper/2508.05994/) (2025)
- [Nighttime Thermal Infrared Image Colorization with Feedback-based Object Appearance Learning](https://mlsanity.com/paper/2310.15688/) (2023)
- [Multi-scale Progressive Feature Embedding for Accurate NIR-to-RGB Spectral Domain Translation](https://mlsanity.com/paper/2312.16040/) (2023)
- [Multimodal Semantic-Aware Automatic Colorization with Diffusion Prior](https://mlsanity.com/paper/2404.16678/) (2024)
- [Transforming Color: A Novel Image Colorization Method](https://mlsanity.com/paper/2410.04799/) (2024)
- [A Novel Deep Learning Method for Thermal to Annotated Thermal-Optical Fused Images](https://mlsanity.com/paper/2107.05942/) (2021)
- [Audio-Infused Automatic Image Colorization by Exploiting Audio Scene Semantics](https://mlsanity.com/paper/2401.13270/) (2024)
- [SwinStyleformer is a favorable choice for image inversion](https://mlsanity.com/paper/2406.13153/) (2024)
- [Computer-aided Colorization State-of-the-science: A Survey](https://mlsanity.com/paper/2410.02288/) (2024)
- [BC-GAN: A Generative Adversarial Network for Synthesizing a Batch of Collocated Clothing](https://mlsanity.com/paper/2502.01080/) (2025)
- [MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model](https://mlsanity.com/paper/2511.18888/) (2025)
- [Testing Neural Networks via Bayesian-Guided Exploration of Decision Landscapes](https://mlsanity.com/paper/2606.04314/) (2026)
- [MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer](https://mlsanity.com/paper/2607.20924/) (2026)

## Abstract (arXiv)

Given a grayscale photograph, the colorization system estimates a visually plausible colorful image. Conventional methods often use semantics to colorize grayscale images. However, in these methods, only classification semantic information is embedded, resulting in semantic confusion and color bleeding in the final colorized image. To address these issues, we propose a fully automatic Saliency Map-guided Colorization with Generative Adversarial Network (SCGAN) framework. It jointly predicts the colorization and saliency map to minimize semantic confusion and color bleeding in the colorized image. Since the global features from pre-trained VGG-16-Gray network are embedded to the colorization encoder, the proposed SCGAN can be trained with much less data than state-of-the-art methods to achieve perceptually reasonable colorization. In addition, we propose a novel saliency map-based guidance method. Branches of the colorization decoder are used to predict the saliency map as a proxy target. Moreover, two hierarchical discriminators are utilized for the generated colorization and saliency map, respectively, in order to strengthen visual perception performance. The proposed system is evaluated on ImageNet validation set. Experimental results show that SCGAN can generate more reasonable colorized images than state-of-the-art techniques.