Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On
cs.RO, cs.AI
Submitted: 2026-11-03
Updated: 2026-11-05
Project page: https://ryan-seungyong-lee.github.io/RoboTryOn
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- DexForce: Extracting Force-informed Actions from Kinesthetic Demonstrations for Dexterous Manipulation
- H2R-Grounder: A Paired-Data-Free Paradigm for Translating Human Interaction Videos into Physically Grounded Robot Videos
- ViViD: Video Virtual Try-on using Diffusion Models
- LTX-2: Efficient Joint Audio-Visual Foundation Model
- EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
- FitDiT: Advancing the Authentic Garment Details for High-fidelity Virtual Try-on
- RLDX-1 Technical Report
- A Closed-Form Geometric Retargeting Solver for Upper Body Humanoid Robot Teleoperation
- Masquerade: Learning from In-the-wild Human Videos using Data-Editing
- Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos
- EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations
- Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
- Mitty: Diffusion-based Human-to-Robot Video Generation
- Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data
- DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation
- EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
- DreamVVT: Mastering Realistic Video Virtual Try-On in the Wild via a Stage-Wise Diffusion Transformer Framework
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation