UniAff: A unified representation of affordances for tool usage and articulation with vision-language models

Q Yu, S Huang, X Yuan, Z Jiang, C Hao, X Li… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Previous studies on robotic manipulation are based on a limited understanding of the
underlying 3D motion constraints and affordances. To address these challenges, we …

PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments

Y You, K **ong, Z Yang, Z Huang, J Zhou, R Shi… - … on Computer Vision, 2024‏ - Springer
Abstract We introduce PACE (Pose Annotations in Cluttered Environments), a large-scale
benchmark designed to advance the development and evaluation of pose estimation …

NeuralLabeling: A versatile toolset for labeling vision datasets using Neural Radiance Fields

F Erich, N Chiba, A Mustafa… - 2024 IEEE/RSJ …, 2024‏ - ieeexplore.ieee.org
We present NeuralLabeling, a labeling approach and toolset for annotating 3D scenes using
either bounding boxes or meshes and generating segmentation masks, affordance maps …

HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos

P Banerjee, S Shkodrani, P Moulon, S Hampali… - arxiv preprint arxiv …, 2024‏ - arxiv.org
We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in
3D. The dataset offers over 833 minutes (more than 3.7 M images) of multi-view …

[HTML][HTML] Learning by Demonstration of a Robot Using One-Shot Learning and Cross-Validation Regression with Z-Score

J Duque-Domingo, M García-Gómez, E Zalama… - Electronics, 2024‏ - mdpi.com
We introduce a One-Shot Learning system where a robot effectively learns how to
manipulate objects by relying solely on the object's name, a single image, and a visual …