TL;DR
ExpertEdit is a novel framework that automatically refines novice motion videos into expert-level performances by learning from unpaired expert demonstrations, enhancing skill transfer without paired data.
Contribution
It introduces a skill-driven motion editing method trained solely on unpaired expert videos, enabling localized skill improvements without manual guidance.
Findings
Outperforms state-of-the-art supervised motion editing methods on multiple metrics.
Effective across eight techniques and three sports, demonstrating versatility.
Learns an expert motion prior using masked language modeling for realistic motion infilling.
Abstract
Visual feedback is critical for motor skill acquisition in sports and rehabilitation, and psychological studies show that observing near-perfect versions of one's own performance accelerates learning more effectively than watching expert demonstrations alone. We propose to enable such personalized feedback by automatically editing a person's motion to reflect higher skill. Existing motion editing approaches are poorly suited for this setting because they assume paired input-output data -- rare and expensive to curate for skill-driven tasks -- and explicit edit guidance at inference. We introduce ExpertEdit, a framework for skill-driven motion editing trained exclusively on unpaired expert video demonstrations. ExpertEdit learns an expert motion prior with a masked language modeling objective that infills masked motion spans with expert-level refinements. At inference, novice motion is…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
