EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices
cs.CV, cs.RO
Submitted: 2026-05-16
Updated: 2026-11-05
Code: https://github.com/physical-superintelligence-lab/HumDex
Project page: https://lucidxr.github.io
Terminology
Sources
- EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
- Project Aria: A New Tool for Egocentric Multi-Modal AI Research
- Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation
- DemoBot: Efficient Learning of Bimanual Manipulation with Dexterous Hands From Third-Person Human Videos
- EgoVLA: Learning Vision-Language-Action Models from Egocentric Human Videos
- Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos
- CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
- InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation
- EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data
- EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration
- mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs
- World Models for Learning Dexterous Hand-Object Interactions from Human Videos
- DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
- SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
- HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations
- HumDex: Humanoid Dexterous Manipulation Made Easy
- ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration
- Moving Through Clutter: Scaling Data Collection and Benchmarking for 3D Scene-Aware Humanoid Locomotion via Virtual Reality
- One Hand to Rule Them All: Canonical Representations for Unified Dexterous Manipulation
- OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs