Saved in:
Bibliographic Details
Main Authors: Xu, Nan, Li, Shiheng, Hou, Shengchao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.20522
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909002982490112
author Xu, Nan
Li, Shiheng
Hou, Shengchao
author_facet Xu, Nan
Li, Shiheng
Hou, Shengchao
contents We propose a new approach for a practical two-stage Optical Music Recognition (OMR) pipeline, with a particular focus on its second stage. Given symbol and event candidates from the visual pipeline, we decode them into an editable, verifiable, and exportable score structure. We focus on complex polyphonic staff notation, especially piano scores, where voice separation and intra-measure timing are the main bottlenecks. Our approach formulates second-stage decoding as a structure decoding problem and uses topology recognition with probability-guided search (BeadSolver) as its core method. We also describe a data strategy that combines procedural generation with recognition-feedback annotations. The result is a practical decoding component for real OMR systems and a path to accumulate structured score data for future end-to-end, multimodal, and RL-style methods.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20522
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Image to Music Language: A Two-Stage Structure Decoding Approach for Complex Polyphonic OMR
Xu, Nan
Li, Shiheng
Hou, Shengchao
Sound
Computer Vision and Pattern Recognition
We propose a new approach for a practical two-stage Optical Music Recognition (OMR) pipeline, with a particular focus on its second stage. Given symbol and event candidates from the visual pipeline, we decode them into an editable, verifiable, and exportable score structure. We focus on complex polyphonic staff notation, especially piano scores, where voice separation and intra-measure timing are the main bottlenecks. Our approach formulates second-stage decoding as a structure decoding problem and uses topology recognition with probability-guided search (BeadSolver) as its core method. We also describe a data strategy that combines procedural generation with recognition-feedback annotations. The result is a practical decoding component for real OMR systems and a path to accumulate structured score data for future end-to-end, multimodal, and RL-style methods.
title From Image to Music Language: A Two-Stage Structure Decoding Approach for Complex Polyphonic OMR
topic Sound
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.20522