中文
相关论文

相关论文: Walk through Paintings: Egocentric World Models fr…

200 篇论文

Egocentric world models present a promising direction for enabling agents to predict and plan, but their performance is constrained by the limited availability of egocentric training data and its inherent partial observability of humans'…

计算机视觉与模式识别 · 计算机科学 2026-05-27 Danny Tran , Roberto Martín-Martín , Kristen Grauman

Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future visual observations based on past observations and…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Amir Bar , Gaoyue Zhou , Danny Tran , Trevor Darrell , Yann LeCun

Training robot policies within a learned world model is trending due to the inefficiency of real-world interactions. The established image-based world models and policies have shown prior success, but lack robust geometric information that…

机器人学 · 计算机科学 2025-09-18 Guanxing Lu , Baoxiong Jia , Puhao Li , Yixin Chen , Ziwei Wang , Yansong Tang , Siyuan Huang

Recent progress in 3D reconstruction has made it easy to create realistic digital twins from everyday environments. However, current digital twins remain largely static and are limited to navigation and view synthesis without embodied…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Byungjun Kim , Taeksoo Kim , Junyoung Lee , Hanbyul Joo

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

Efficient navigation in dynamic environments requires anticipating how motion patterns evolve beyond the robot's immediate perceptual range, enabling preemptive rather than purely reactive planning in crowded scenes. Maps of Dynamics (MoDs)…

机器人学 · 计算机科学 2026-03-03 Iacopo Catalano , David Morilla-Cabello , Jorge Pena-Queralta , Eduardo Montijano

Action-conditioned world models (ACWMs) have shown strong promise for video prediction and decision-making. However, existing benchmarks are largely restricted to egocentric navigation or narrow, task-specific robotics datasets, offering…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Haotian Xue , Yipu Chen , Liqian Ma , Zelin Zhao , Lama Moukheiber , Yuchen Zhu , Yongxin Chen

World models enable agents to plan by imagining future states, but existing approaches operate from a single viewpoint, typically egocentric, even when other perspectives would make planning easier; navigation, for instance, benefits from a…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Rishabh Sharma , Gijs Hogervorst , Wayne E. Mackey , David J. Heeger , Stefano Martiniani

World models, which predict future transitions from past observation and action sequences, have shown great promise for improving data efficiency in sequential decision-making. However, existing world models often require extensive…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Siqiao Huang , Jialong Wu , Qixing Zhou , Shangchen Miao , Mingsheng Long

Generating instructional images of human daily actions from an egocentric viewpoint serves as a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to…

计算机视觉与模式识别 · 计算机科学 2024-03-25 Bolin Lai , Xiaoliang Dai , Lawrence Chen , Guan Pang , James M. Rehg , Miao Liu

Video diffusion models have recently achieved remarkable progress in realism and controllability. However, achieving seamless video translation across different perspectives, such as first-person (egocentric) and third-person (exocentric),…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Quanjian Song , Yiren Song , Kelly Peng , Yuan Gao , Mike Zheng Shou

World models enable planning in imagined future predicted space, offering a promising framework for embodied navigation. However, existing navigation world models often lack action-conditioned consistency, so visually plausible predictions…

计算机视觉与模式识别 · 计算机科学 2026-03-10 Han Yan , Zishang Xiang , Zeyu Zhang , Hao Tang

World models are widely explored in embodied intelligence, yet they typically predict distinct evolutions of the world and the ego within a single stream, where the world captures persistent instruction-agnostic scene regularities and the…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Zuyao Lin , Jianhui Zhang , Peidong Jia , Xiaoguang Zhao , Shanghang Zhang , Xingyu Chen

World models have become a central paradigm for learning predictive simulators that support generation, planning, and decision-making. Yet, despite rapid progress in industry-scale interactive video generation, the broader research…

计算机视觉与模式识别 · 计算机科学 2026-05-29 Siqiao Huang , Partha Kaushik , Michael Chen , Hengkai Pan , Kaiwen Geng , Omar Chehab , Fernando Moreno-Pino , Max Simchowitz

Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that decouple navigation planning from visual world modeling,…

Egocentric action anticipation is the task of predicting the future actions a camera wearer will likely perform based on past video observations. While in a real-world system it is fundamental to output such predictions before the action…

计算机视觉与模式识别 · 计算机科学 2022-05-11 Antonino Furnari , Giovanni Maria Farinella

Embodied agents in household environments must plan under partial observation: they need to remember objects, track state changes, and recover when actions fail. Existing benchmarks only partially test this ability. Egocentric video…

人工智能 · 计算机科学 2026-05-14 Qinchuan Cheng , Zhantao Gong , Pengzhan Sun , Angela Yao , Xulei Yang , Shijie Li

Imitation learning has emerged as a promising approach towards building generalist robots. However, scaling imitation learning for large robot foundation models remains challenging due to its reliance on high-quality expert demonstrations.…

机器人学 · 计算机科学 2025-05-26 Chuning Zhu , Raymond Yu , Siyuan Feng , Benjamin Burchfiel , Paarth Shah , Abhishek Gupta

Wearable collaborative robots stand to assist human wearers who need fall prevention assistance or wear exoskeletons. Such a robot needs to be able to constantly adapt to the surrounding scene based on egocentric vision, and predict the ego…

计算机视觉与模式识别 · 计算机科学 2024-08-08 Weizhuo Wang , C. Karen Liu , Monroe Kennedy

Generative world models have shown promise for simulating dynamic environments, yet egocentric video remains challenging due to rapid viewpoint changes, frequent hand-object interactions, and goal-directed procedures whose evolution depends…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Yifan Shen , Jiateng Liu , Xinzhuo Li , Yuanzhe Liu , Bingxuan Li , Houze Yang , Wenqi Jia , Yijiang Li , Tianjiao Yu , James Matthew Rehg , Xu Cao , Ismini Lourentzou
‹ 上一页 1 2 3 10 下一页 ›