paper-with-me

홈 › Papers

Observer-Actor: Active Vision Imitation Learning with Sparse-View Gaussian Splatting

2025-11-22 · Yilong Wang, Cheng Qian, Ruomeng Fan, Edward Johns arxiv

We propose Observer Actor (ObAct), a novel framework for active vision imitation learning in which the observer moves to optimal visual observations for the actor. We study ObAct on a dual-arm robotic system equipped with wrist-mounted cameras. At test time, ObAct dynamically assigns observer and actor roles: the observer arm constructs a 3D Gaussian Splatting (3DGS) representation from three images, virtually explores this to find an optimal camera pose, then moves to this pose; the actor arm then executes a policy using the observer's observations. This formulation enhances the clarity and visibility of both the object and the gripper in the policy's observations. As a result, we enable the training of ambidextrous policies on observations that remain closer to the occlusion-free training distribution, leading to more robust policies. We study this formulation with two existing imitation learning methods -- trajectory transfer and behavior cloning -- and experiments show that ObAct significantly outperforms static-camera setups: trajectory transfer improves by 145% without occlusion and 233% with occlusion, while behavior cloning improves by 75% and 143%, respectively. Videos are available at https://obact.github.io.

📄 PDF Abstract BibTeX arXiv:2511.18140

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

PESAO: Psychophysical Experimental Setup for Active Observers

2020-09-15 · Markus D. Solbach, John K. Tsotsos

Most past and present research in computer vision involves passively observed data. Humans, however, are active observers outside the lab; they explore, search, select what and how to look. Nonetheless, how exactly activ…

DOB-Net: Actively Rejecting Unknown Excessive Time-Varying Disturbances

2019-07-10 · Tianming Wang, Wen-jie Lu, Zheng Yan, Dikai Liu

This paper presents an observer-integrated Reinforcement Learning (RL) approach, called Disturbance OBserver Network (DOB-Net), for robots operating in environments where disturbances are unknown and time-varying, and ma…

PositionReinforcement LearningReinforcement Learning (RL)

Actor and Observer: Joint Modeling of First and Third-Person Videos

2018-04-25 · CVPR 2018 6 · Gunnar A. Sigurdsson, Abhinav Gupta, Cordelia Schmid, Ali Farhadi 외

Several theories in cognitive neuroscience suggest that when people interact with the world, or simulate interactions, they do so from a first-person egocentric perspective, and seamlessly transfer knowledge between thir…

Action RecognitionTemporal Action Localization

Towards Active Vision for Action Localization with Reactive Control and Predictive Learning

2021-11-09 · Shubham Trehan, Sathyanarayanan N. Aakur

Visual event perception tasks such as action localization have primarily focused on supervised learning settings under a static observer, i.e., the camera is static and cannot be controlled by an algorithm. They are ofte…

Action LocalizationDiversityObject Tracking

Probabilistic Active Goal Recognition

2025-07-29 · Chenyuan Zhang, Cristian Rojas Cardenas, Hamid Rezatofighi, Mor Vered 외 arxiv

In multi-agent environments, effective interaction hinges on understanding the beliefs and intentions of other agents. While prior work on goal recognition has largely treated the observer as a passive reasoner, Active G…