paper-with-me

홈 › Papers

One-Shot Imitation Learning: A Pose Estimation Perspective

2023-10-18 · Pietro Vitiello, Kamil Dreczkowski, Edward Johns

In this paper, we study imitation learning under the challenging setting of: (1) only a single demonstration, (2) no further data collection, and (3) no prior task or object knowledge. We show how, with these constraints, imitation learning can be formulated as a combination of trajectory transfer and unseen object pose estimation. To explore this idea, we provide an in-depth study on how state-of-the-art unseen object pose estimators perform for one-shot imitation learning on ten real-world tasks, and we take a deep dive into the effects that camera calibration, pose estimation error, and spatial generalisation have on task success rates. For videos, please visit https://www.robot-learning.uk/pose-estimation-perspective.

📄 PDF Abstract BibTeX arXiv:2310.12077

Code (0)

등록된 구현이 없습니다.

Tasks

Camera CalibrationImitation LearningObjectPose Estimation

Similar Papers 제목 키워드 기반

DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images

2026-06-10 · Pengfei Wang, Shihao Wang, Liyi Chen, Zhiyuan Ma 외 arxiv

While monocular depth estimation has achieved significant progress, achieving generalized metric depth estimation for both narrow field-of-view (FoV) perspectives and $360^\circ$ panoramas remains an unsolved challenge. …

Monocular Depth Estimation

Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation

2019-09-27 · Xinlei Pan, Tingnan Zhang, Brian Ichter, Aleksandra Faust 외

Imitation learning is a popular approach for training visual navigation policies. However, collecting expert demonstrations for legged robots is challenging as these robots can be hard to control, move slowly, and cannot…

DisentanglementImitation LearningVisual Navigation

Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

2025-01-05 · CVPR 2025 1 · Yuliang Guo, Sparsh Garg, S. Mahdi H. Miangoleh, Xinyu Huang 외

While recent depth foundation models exhibit strong zero-shot generalization, achieving accurate metric depth across diverse camera types-particularly those with large fields of view (FoV) such as fisheye and 360-degree …

Data AugmentationDepth EstimationERPZero-shot Generalization

Investigating More Explainable and Partition-Free Compositionality Estimation for LLMs: A Rule-Generation Perspective

2026-04-30 · Ziyao Xu, Cong Wang, Houfeng Wang arxiv

Compositional generalization tests are often used to estimate the compositionality of LLMs. However, such tests have the following limitations: (1) they only focus on the output results without considering LLMs' understa…

Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation

2024-06-18 · Ning-Hsu Wang, Yu-Lun Liu

Accurately estimating depth in 360-degree imagery is crucial for virtual reality, autonomous navigation, and immersive media applications. Existing depth estimation methods designed for perspective-view imagery fail when…

Autonomous NavigationData AugmentationDepth EstimationMonocular Depth Estimation+1