PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xuan, Ruan, Kai, Han, Jiayi, Zhou, Kaiyue, Wang, Gaoang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918446875279360
author Wang, Xuan
Ruan, Kai
Han, Jiayi
Zhou, Kaiyue
Wang, Gaoang
author_facet Wang, Xuan
Ruan, Kai
Han, Jiayi
Zhou, Kaiyue
Wang, Gaoang
contents Audio-driven bimanual piano motion generation requires precise modeling of complex musical structures and dynamic cross-hand coordination. However, existing methods often rely on acoustic-only representations lacking symbolic priors, employ inflexible interaction mechanisms, and are limited to computationally expensive short-sequence generation. To address these limitations, we propose PianoFlow, a flow-matching framework for precise and coordinated bimanual piano motion synthesis. Our approach strategically leverages MIDI as a privileged modality during training, distilling these structured musical priors to achieve deep semantic understanding while maintaining audio-only inference. Furthermore, we introduce an asymmetric role-gated interaction module to explicitly capture dynamic cross-hand coordination through role-aware attention and temporal gating. To enable real-time streaming generation for arbitrarily long sequences, we design an autoregressive flow continuation scheme that ensures seamless cross-chunk temporal coherence. Extensive experiments on the PianoMotion10M dataset demonstrate that PianoFlow achieves superior quantitative and qualitative performance, while accelerating inference by over 9\times compared to previous methods.
format Preprint
id arxiv_https___arxiv_org_abs_2604_12856
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination
Wang, Xuan
Ruan, Kai
Han, Jiayi
Zhou, Kaiyue
Wang, Gaoang
Computer Vision and Pattern Recognition
Audio-driven bimanual piano motion generation requires precise modeling of complex musical structures and dynamic cross-hand coordination. However, existing methods often rely on acoustic-only representations lacking symbolic priors, employ inflexible interaction mechanisms, and are limited to computationally expensive short-sequence generation. To address these limitations, we propose PianoFlow, a flow-matching framework for precise and coordinated bimanual piano motion synthesis. Our approach strategically leverages MIDI as a privileged modality during training, distilling these structured musical priors to achieve deep semantic understanding while maintaining audio-only inference. Furthermore, we introduce an asymmetric role-gated interaction module to explicitly capture dynamic cross-hand coordination through role-aware attention and temporal gating. To enable real-time streaming generation for arbitrarily long sequences, we design an autoregressive flow continuation scheme that ensures seamless cross-chunk temporal coherence. Extensive experiments on the PianoMotion10M dataset demonstrate that PianoFlow achieves superior quantitative and qualitative performance, while accelerating inference by over 9\times compared to previous methods.
title PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.12856