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

Source: [PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination](<https://www.sota2.com/research/paper/69df1bc37d0172140ec7bb79>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-17T05:00:04.440Z

Authors: Xuan Wang, Kai Ruan, Jiayi Han, Kaiyue Zhou, Gaoang Wang

Published: 2026-04-14T15:07:21.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Piano Motion Generation on PianoMotion10M short-sequence 1.0](<https://www.sota2.com/research/sota/piano-motion-generation-on-pianomotion10m-short-sequence-1-0.md>): Piano Motion Generation; PianoMotion10M short-sequence 1.0; FGD (Left Hand): 0.266.

- [Piano Motion Generation on PianoMotion10M long-sequence setting](<https://www.sota2.com/research/sota/piano-motion-generation-on-pianomotion10m-long-sequence-setting.md>): Piano Motion Generation; PianoMotion10M long-sequence setting; Left Hand FGD: 0.309.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.12856>)

[PDF](<https://arxiv.org/pdf/2604.12856.pdf>)