AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

End-to-End Full-Page Optical Music Recognition for Pianoform Sheet Music

Antonio Ríos-Vila, Jorge Calvo-Zaragoza, David Rizo, Thierry Paquet

IJCV 2026 · Image generation › Autoregressive and latent generation · approach: Controllable music generation · 17 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace CNN backbone with ConvNeXtSMT (bekern) · FP-GrandStaff test (synthetic)SER: 19.7 -> 6.9Improved
use ekern encoding instead of raw kernSMT-ConvNeXt · FP-GrandStaff test (synthetic)SER: 9.7 -> 8.5Improved
use bekern encoding instead of raw kernSMT-ConvNeXt · FP-GrandStaff test (synthetic)SER: 9.7 -> 6.9Improved
use ekern encoding instead of raw kernSMT-CNN · FP-GrandStaff test (synthetic)CER: 15.8 -> 17.3Hurt
add system-level pre-training (ablation)SMT-ConvNeXt · FP-GrandStaff test (synthetic)SER: 12.4 -> 6.9Improved
add incremental curriculum learning (ablation)SMT-ConvNeXt · FP-GrandStaff test (synthetic)SER: 9.8 -> 6.9Improved
add both pre-training and curriculum to baseline (ablation)SMT-ConvNeXt · FP-GrandStaff test (synthetic)SER: 42.6 -> 6.9Improved
add system-level pre-training only (ablation)SMT-ConvNeXt · FP-GrandStaff test (synthetic)SER: 42.6 -> 9.8Improved
add 1D positional encoding vs none (ablation)SMT-ConvNeXt · FP-GrandStaff test (synthetic)SER: 78.4 -> 15.57Improved
use 2D instead of 1D positional encoding (ablation)SMT-ConvNeXt · FP-GrandStaff test (synthetic)SER: 15.57 -> 6.9Improved
train on more systems per page (max 1 -> 5) and test on 2 systems (ablation)SMT-ConvNeXt · Synthetic curriculum matrixSER: 48.7 -> 4.91Improved
fine-tune on real scores (ablation)SMT-ConvNeXt · Mozarteum (real)SER: 38.9 -> 14.1Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy