ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos

arXiv:2604.10466v1 Announce Type: new 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 masked at skill-critical moments and projected into the learned expert manifold, producing localized skill improvements without paired supervision or manual edit guidance. Across eight diverse techniques and three sports from Ego-Exo4D and Karate Kyokushin, ExpertEdit outperforms state-of-the-art supervised motion editing methods on multiple metrics of motion realism and expert quality. Project page: https://vision.cs.utexas.edu/projects/expert_edit/ .

Related

• InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation
• ImVideoEdit: Image-learning Video Editing via 2D Spatial Difference Attention Blocks
• Structure-Aware Fine-Grained Gaussian Splatting for Expressive Avatar Reconstruction
• PianoFlow: Music-Aware Streaming Piano Motion Generation with Bimanual Coordination
• Point Prompting: Counterfactual Tracking with Video Diffusion Models

Source: arXiv cs.CV | 2026-04-14