RobotAR: An Augmented Reality Compatible Teleconsulting Robotics Toolkit for Augmented Makerspace Experiences

by Ana Villanueva | Jun 7, 2021 | 2021, Ana Villanueva, Featured Publications, Karthik Ramani, Karthik Ramani, Publications, Recent Publications, Zhengzhe Zhu, Ziyi Liu

Distance learning is facing a critical moment finding a balance between high quality education for remote students and engaging them in hands-on learning. This is particularly relevant for project-based classrooms and makerspaces, which typically require extensive...

AdapTutAR: An Adaptive Tutoring System for Machine Tasks in Augmented Reality

by Xun Qian | Jun 6, 2021 | 2021, Karthik Ramani, Karthik Ramani, Publications, Recent Publications, Tianyi Wang, Xun Qian, Yuanzhi Cao

Modern manufacturing processes are in a state of flux, as they adapt to increasing demand for flexible and self-configuring production. This poses challenges for training workers to rapidly master new machine operations and processes, i.e. machine tasks. Conventional...

VRFromX: From Scanned Reality to Interactive Virtual Experience with Human-in-the-Loop

by Ananya Ipsita | Jun 5, 2021 | 2021, Ananya Ipsita, Karthik Ramani, Karthik Ramani, Min Liu, Publications, Recent Publications, Subramanian Chidambaram, Yuanzhi Cao

There is an increasing trend of Virtual-Reality (VR) applications found in education, entertainment, and industry. Many of them utilize real world tools, environments, and interactions as bases for creation. However, creating such applications is tedious, fragmented,...

Object Synthesis by Learning Part Geometry with Surface and Volumetric Representations

by Sangpil Kim | Aug 28, 2020 | 2020, Future of Work, Hyunggun Chi, Karthik Ramani, Publications, Recent Publications, Sangpil Kim

Abstract: We propose a conditional generative model, named Part Geometry Network (PG-Net), which synthesizes realistic objects and can be used as a robust feature descriptor for object reconstruction and classification. Surface and volumetric representations of...

First-Person View Hand Segmentation of Multi-Modal Hand Activity Video Dataset

by Sangpil Kim | Aug 7, 2020 | 2020, Convergence Accelerator, Future of Work, Hyunggun Chi, Karthik Ramani, Publications, Recent Publications, Sangpil Kim

Abstract:  First-person-view videos of hands interacting with tools are widely used in the computer vision industry. However, creating a dataset with pixel-wise segmentation of hands is challenging since most videos are captured with fingertips occluded by the hand...

A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks

by Sangpil Kim | Jul 3, 2020 | 2020, CISE Research Infrastructure, Convergence Accelerator, Future of Work, Hyunggun Chi, Karthik Ramani, Karthik Ramani, Publications, Recent Publications, Sangpil Kim

We introduce a large-scale annotated mechanical components benchmark for classification and retrieval tasks named Mechanical Components Benchmark (MCB): a large-scale dataset of 3D objects of mechanical components. The dataset enables data-driven feature learning for...