ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos
- URL: http://arxiv.org/abs/2604.10466v1
- Date: Sun, 12 Apr 2026 05:25:33 GMT
- Title: ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos
- Abstract summary: ExpertEdit is a framework for skill-driven motion editing trained exclusively on unpaired expert video demonstrations.<n>It produces localized skill improvements without paired supervision or manual edit guidance.<n>It outperforms state-of-the-art supervised motion editing methods on multiple metrics of motion realism and expert quality.
- Score: 50.06747687804514
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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 papers
- SportSkills: Physical Skill Learning from Sports Instructional Videos [51.16409727318035]
SportSkills is the first large-scale sports dataset geared towards physical skill learning with in-the-wild video.<n>We show that SportSkills unlocks the ability to understand fine-grained differences between physical actions.<n>We introduce the first large-scale task formulation of mistake-conditioned instructional video retrieval.
arXiv Detail & Related papers (2026-03-26T08:29:35Z) - Versatile Editing of Video Content, Actions, and Dynamics without Training [57.167192591765456]
We introduce DynaEdit, a training-free editing method that unlocks versatile video editing capabilities with pretrained text-to-video flow models.<n>We show that DynaEdit achieves state-of-the-art results on complex text-based video editing tasks, including modifying actions, inserting objects that interact with the scene, and introducing global effects.
arXiv Detail & Related papers (2026-03-18T17:50:56Z) - CoEditor++: Instruction-based Visual Editing via Cognitive Reasoning [98.98349220451216]
CoEditor++ is a training-free framework that decomposes editing into "what to edit" and "how to edit"<n>We show that CoEditor++ achieves state-of-the-art performance in both general editing and responsible editing tasks.<n>Our findings suggest the potential toward cognitive-centric instruction-based image editing.
arXiv Detail & Related papers (2026-01-31T12:20:46Z) - Learning Skill-Attributes for Transferable Assessment in Video [56.813876909367856]
Skill assessment from video entails rating the quality of a person's physical performance and explaining what could be done better.<n>Our CrossTrainer approach discovers skill-attributes, such as balance, control, and hand positioning.<n>By abstracting out the shared behaviors indicative of human skill, the proposed video representation generalizes substantially better than an array of existing techniques.
arXiv Detail & Related papers (2025-11-17T23:53:06Z) - InstructVEdit: A Holistic Approach for Instructional Video Editing [28.13673601495108]
InstructVEdit is a full-cycle instructional video editing approach that establishes a reliable dataset curation workflow.<n>It incorporates two model architectural improvements to enhance edit quality while preserving temporal consistency.<n>It also proposes an iterative refinement strategy leveraging real-world data to enhance generalization and minimize train-test discrepancies.
arXiv Detail & Related papers (2025-03-22T04:12:20Z) - A Reinforcement Learning-Based Automatic Video Editing Method Using Pre-trained Vision-Language Model [10.736207095604414]
We propose a two-stage scheme for general editing. Firstly, unlike previous works that extract scene-specific features, we leverage the pre-trained Vision-Language Model (VLM)
We also propose a Reinforcement Learning (RL)-based editing framework to formulate the editing problem and train the virtual editor to make better sequential editing decisions.
arXiv Detail & Related papers (2024-11-07T18:20:28Z) - ExpertAF: Expert Actionable Feedback from Video [81.46431188306397]
We introduce a novel method to generate actionable feedback from video of a person doing a physical activity, such as basketball or soccer.<n>Our method takes a video demonstration and its accompanying 3D body pose and generates expert commentary describing what the person is doing well and what they could improve.<n>We show how to leverage Ego-Exo4D's [29] videos of skilled activity and expert commentary together with a strong language model to create a weakly-supervised training dataset for this task.
arXiv Detail & Related papers (2024-08-01T16:13:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.