mlsanityData to 14 Oct 2026

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

arXiv 2411.16405 ↗First posted 25 Nov 2024cs.CV cs.AI eess.IVcited by 3

Not on the map. Why?

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.

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

21 of 46 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  3. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  6. 2016Improved Techniques for Training GANscited by 2,970
  7. 2017Improved Training of Wasserstein GANscited by 2,235
  8. 2014Conditional Generative Adversarial Netscited by 2,162
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  11. 2022Diffusion Models in Vision: A Surveycited by 1,015
  12. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
9 more
  1. 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 123
  2. 2020Hierarchical Amortized Training for Memory-efficient High Resolution 3D GANcited by 60
  3. 2019Understanding Optical Music Recognitioncited by 37
  4. 2024Sheet Music Transformer: End-To-End Optical Music Recognition Beyond Monophonic Transcriptioncited by 20
  5. 2017Optical Music Recognition with Convolutional Sequence-to-Sequence Modelscited by 12
  6. 2020Optical Music Recognition: State of the Art and Major Challengescited by 12
  7. 2021DoReMi: First glance at a universal OMR datasetcited by 10
  8. 2022Conditional Progressive Generative Adversarial Network for satellite image generationcited by 4
  9. 2024Knowledge Discovery in Optical Music Recognition: Enhancing Information Retrieval with Instance Segmentationcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Unified Cross-modal Translation of Score Images, Symbolic Music, and Performance Audiocited by 6
  2. 2026Optical Music Recognition for Real-World Manuscripts with Synthetic Datacited by 1
  3. 2025GAN-based Content-Conditioned Generation of Handwritten Musical Symbolscited by 0