Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.09692 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915931480915968 |
|---|---|
| author | Bae, Joonhyung Kim, Kirak Cho, Hyeyoon Lee, Sein Choi, Yoon-Seok Hur, Hyeon Lee, Gyubin Maezawa, Akira Obata, Satoshi Park, Jonghwa Park, Jaebum Nam, Juhan |
| author_facet | Bae, Joonhyung Kim, Kirak Cho, Hyeyoon Lee, Sein Choi, Yoon-Seok Hur, Hyeon Lee, Gyubin Maezawa, Akira Obata, Satoshi Park, Jonghwa Park, Jaebum Nam, Juhan |
| contents | Synthesizing realistic piano hand motions requires both precision and naturalness. Physics-based methods achieve precision but produce stiff motions; data-driven models learn natural dynamics but struggle with positional accuracy. Piano motion exhibits a natural hierarchy: fingertip positions are nearly deterministic given piano geometry and fingering, while wrist and intermediate joints offer stylistic freedom. We present [OURS], a four-stage framework exploiting this hierarchy: (1) statistics-based fingertip positioning, (2) FiLM-conditioned trajectory refinement, (3) wrist estimation, and (4) STGCN-based pose synthesis. We contribute expert-annotated fingerings for the FürElise dataset (153 pieces, ~10 hours). Experiments demonstrate F1 = 0.910, substantially outperforming diffusion baselines (F1 = 0.121), with user study (N=41) confirming quality approaching motion capture. Expert evaluation by professional pianists (N=5) identified anticipatory motion as the key remaining gap, providing concrete directions for future improvement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09692 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tipiano: Cascaded Piano Hand Motion Synthesis via Fingertip Priors Bae, Joonhyung Kim, Kirak Cho, Hyeyoon Lee, Sein Choi, Yoon-Seok Hur, Hyeon Lee, Gyubin Maezawa, Akira Obata, Satoshi Park, Jonghwa Park, Jaebum Nam, Juhan Artificial Intelligence Computer Vision and Pattern Recognition Synthesizing realistic piano hand motions requires both precision and naturalness. Physics-based methods achieve precision but produce stiff motions; data-driven models learn natural dynamics but struggle with positional accuracy. Piano motion exhibits a natural hierarchy: fingertip positions are nearly deterministic given piano geometry and fingering, while wrist and intermediate joints offer stylistic freedom. We present [OURS], a four-stage framework exploiting this hierarchy: (1) statistics-based fingertip positioning, (2) FiLM-conditioned trajectory refinement, (3) wrist estimation, and (4) STGCN-based pose synthesis. We contribute expert-annotated fingerings for the FürElise dataset (153 pieces, ~10 hours). Experiments demonstrate F1 = 0.910, substantially outperforming diffusion baselines (F1 = 0.121), with user study (N=41) confirming quality approaching motion capture. Expert evaluation by professional pianists (N=5) identified anticipatory motion as the key remaining gap, providing concrete directions for future improvement. |
| title | Tipiano: Cascaded Piano Hand Motion Synthesis via Fingertip Priors |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.09692 |