中文
相关论文

相关论文: AoE: Always-on Egocentric Human Video Collection f…

200 篇论文

We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for continuous simulation. Existing egocentric simulators either…

计算机视觉与模式识别 · 计算机科学 2026-04-02 Jinkun Hao , Mingda Jia , Ruiyan Wang , Xihui Liu , Ran Yi , Lizhuang Ma , Jiangmiao Pang , Xudong Xu

The advancement of robot learning is currently hindered by the scarcity of large-scale, high-quality datasets. While established data collection methods such as teleoperation and universal manipulation interfaces dominate current datasets,…

To serve as a scalable data source for embodied AI, world models should act as true simulators that infer interaction dynamics strictly from user actions, rather than mere conditional video generators relying on privileged future object…

计算机视觉与模式识别 · 计算机科学 2026-03-17 Dayou Li , Lulin Liu , Bangya Liu , Shijie Zhou , Jiu Feng , Ziqi Lu , Minghui Zheng , Chenyu You , Zhiwen Fan

The scale and diversity of demonstration data required for imitation learning is a significant challenge. We present EgoMimic, a full-stack framework which scales manipulation via human embodiment data, specifically egocentric human videos…

机器人学 · 计算机科学 2024-11-01 Simar Kareer , Dhruv Patel , Ryan Punamiya , Pranay Mathur , Shuo Cheng , Chen Wang , Judy Hoffman , Danfei Xu

Embodied AI (EAI) agents continuously interact with the physical world, generating vast, heterogeneous multimodal data streams that traditional management systems are ill-equipped to handle. In this survey, we first systematically evaluate…

机器人学 · 计算机科学 2025-08-20 Yihao Lu , Hao Tang

Egocentric video is increasingly used as a data source for robot learning, activity understanding, and embodied AI research, but collecting it at scale remains fragmented in practice: each candidate host device, such as an Android phone,…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Liuchuan Yu , Erdem Murat , Beichen Wang , Yan Zeng , Tingting Luo , Huizhen Zhou , Shanghao Li , Huining Feng , Zhigen Zhao , Ning Yang , Ke Jing , Yunhao Liu , Ruoya Sheng

The recent advancement of Vision Language Action (VLA) models has driven a critical demand for large scale egocentric datasets. However, existing datasets are often limited by short episode durations, typically spanning only a few minutes,…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Senthil Palanisamy , Abhishek Anand , Satpal Singh Rathor , Pratyush Patnaik , Shubhanshu Khatana , Ekaksh Janweja

Imitation learning from human demonstrations offers a promising approach for robot skill acquisition, but egocentric human data introduces fundamental challenges due to the embodiment gap. During manipulation, humans actively coordinate…

机器人学 · 计算机科学 2026-03-11 Justin Yu , Yide Shentu , Di Wu , Pieter Abbeel , Ken Goldberg , Philipp Wu

What if accessing the web did not require a screen, a stable desk, or even free hands? For people navigating crowded cities, living with low vision, or experiencing cognitive overload, smart glasses coupled with AI agents could turn the web…

This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI. Unlike prior studies that explored this as long-form video understanding and utilized…

计算机视觉与模式识别 · 计算机科学 2025-01-10 Yue Fan , Xiaojian Ma , Rongpeng Su , Jun Guo , Rujie Wu , Xi Chen , Qing Li

Human demonstrations offer rich environmental diversity and scale naturally, making them an appealing alternative to robot teleoperation. While this paradigm has advanced robot-arm manipulation, its potential for the more challenging,…

机器人学 · 计算机科学 2026-02-11 Modi Shi , Shijia Peng , Jin Chen , Haoran Jiang , Yinghui Li , Di Huang , Ping Luo , Hongyang Li , Li Chen

Robot learning increasingly depends on large and diverse data, yet robot data collection remains expensive and difficult to scale. Egocentric human data offer a promising alternative by capturing rich manipulation behavior across everyday…

Human behaviors in the real world naturally encode rich, long-term contextual information that can be leveraged to train embodied agents for perception, understanding, and acting. However, existing capture systems typically rely on costly…

计算机视觉与模式识别 · 计算机科学 2026-04-03 Wenjia Wang , Liang Pan , Huaijin Pi , Yuke Lou , Xuqian Ren , Yifan Wu , Zhouyingcheng Liao , Lei Yang , Rishabh Dabral , Christian Theobalt , Taku Komura

Understanding the world in first-person view is fundamental in Augmented Reality (AR). This immersive perspective brings dramatic visual changes and unique challenges compared to third-person views. Synthetic data has empowered…

计算机视觉与模式识别 · 计算机科学 2024-04-12 Gen Li , Kaifeng Zhao , Siwei Zhang , Xiaozhong Lyu , Mihai Dusmanu , Yan Zhang , Marc Pollefeys , Siyu Tang

Human egocentric video captures rich manipulation demonstrations without any robot hardware, yet transferring these skills to robots remains challenging due to the embodiment gap between human and robot in both visual appearance and…

机器人学 · 计算机科学 2026-05-29 Zhi Wang , Botao He , Kelin Yu , Seungjae Lee , Ruohan Gao , Furong Huang , Yiannis Aloimonos

Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusion…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Enrico Pallotta , Sina Mokhtarzadeh Azar , Lars Doorenbos , Serdar Ozsoy , Umar Iqbal , Juergen Gall

Egocentric assistants often rely on first-person view data to capture user behavior and context for personalized services. Since different users exhibit distinct habits, preferences, and routines, such personalization is essential for truly…

计算机视觉与模式识别 · 计算机科学 2026-04-23 Yanshuo Wang , Yuan Xu , Xuesong Li , Jie Hong , Yizhou Wang , Chang Wen Chen , Wentao Zhu

Egocentric human video data, which captures rich human-environment interactions and can be collected at scale, has become a key driver of embodied intelligence research. However, existing egocentric datasets typically lack tactile sensing,…

As embodied models become powerful, humans will collaborate with multiple embodied AI agents at their workplace or home in the future. To ensure better communication between human users and the multi-agent system, it is crucial to interpret…

计算机视觉与模式识别 · 计算机科学 2026-03-12 Kangsan Kim , Yanlai Yang , Suji Kim , Woongyeong Yeo , Youngwan Lee , Mengye Ren , Sung Ju Hwang

Large language models leverage internet-scale text data, yet embodied AI remains constrained by the prohibitive costs of physical trajectory collection. Desktop environments -- particularly gaming -- offer a compelling alternative: they…

‹ 上一页 1 2 3 10 下一页 ›