# Synthesising Handwritten Music with GANs: A Comprehensive Evaluation of CycleWGAN, ProGAN, and DCGAN

arXiv: https://arxiv.org/abs/2411.16405 · HTML: https://mlsanity.com/paper/2411.16405/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 25 Nov 2024.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [R-FCN: Object Detection via Region-based Fully Convolutional Networks](https://mlsanity.com/paper/1605.06409/) (2016)
- [Pros and Cons of GAN Evaluation Measures: New Developments](https://mlsanity.com/paper/2103.09396/) (2021)
- [Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN](https://mlsanity.com/paper/2008.01910/) (2020)
- [Understanding Optical Music Recognition](https://mlsanity.com/paper/1908.03608/) (2019)
- [Sheet Music Transformer: End-To-End Optical Music Recognition Beyond Monophonic Transcription](https://mlsanity.com/paper/2402.07596/) (2024)
- [Optical Music Recognition with Convolutional Sequence-to-Sequence Models](https://mlsanity.com/paper/1707.04877/) (2017)
- [Optical Music Recognition: State of the Art and Major Challenges](https://mlsanity.com/paper/2006.07885/) (2020)
- [DoReMi: First glance at a universal OMR dataset](https://mlsanity.com/paper/2107.07786/) (2021)
- [Conditional Progressive Generative Adversarial Network for satellite image generation](https://mlsanity.com/paper/2211.15303/) (2022)
- [Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentation](https://mlsanity.com/paper/2408.15002/) (2024)

## Built on by (most cited first, 3 of 3)

- [Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audio](https://mlsanity.com/paper/2505.12863/) (2025)
- [Optical Music Recognition for Real-World Manuscripts with Synthetic Data](https://mlsanity.com/paper/2606.09479/) (2026)
- [GAN-based Content-Conditioned Generation of Handwritten Musical Symbols](https://mlsanity.com/paper/2510.17869/) (2025)

## Abstract (arXiv)

The generation of handwritten music sheets is a crucial step toward enhancing Optical Music Recognition (OMR) systems, which rely on large and diverse datasets for optimal performance. However, handwritten music sheets, often found in archives, present challenges for digitisation due to their fragility, varied handwriting styles, and image quality. This paper addresses the data scarcity problem by applying Generative Adversarial Networks (GANs) to synthesise realistic handwritten music sheets. We provide a comprehensive evaluation of three GAN models - DCGAN, ProGAN, and CycleWGAN - comparing their ability to generate diverse and high-quality handwritten music images. The proposed CycleWGAN model, which enhances style transfer and training stability, significantly outperforms DCGAN and ProGAN in both qualitative and quantitative evaluations. CycleWGAN achieves superior performance, with an FID score of 41.87, an IS of 2.29, and a KID of 0.05, making it a promising solution for improving OMR systems.