Many activation values of Convolutional Neural Networks (CNNs) are zeros due to ReLU
(Rectified Linear Unit), one of the most common activation functions used in modern neural …

For autonomous driving, it is imperative to perform various high-computation image
recognition tasks with high accuracy, utilizing diverse sensors to perceive the surrounding …

To understand how well a proposed augmented reality (AR) solution works, existing papers
often conducted tailored and isolated evaluations for specific AR tasks, eg, depth or lighting …

Accurate metric depth can help achieve more realistic user interactions such as object
placement and occlusion detection in mobile augmented reality (AR). However, it can be …

High-resolution depth estimation, with a minimum resolution of, is essential for achieving
more immersive experiences in on-device 3D vision applications. However, implementing …

We present a deep neural network‐based method that acquires high‐quality shape and
spatially varying reflectance of 3D objects using smartphone multi‐lens imaging. Our …

The modern university computer lab and kindergarden through 12th grade classrooms
require a centralized solution to efficiently manage a large number of desktops. The existing …

In this study, the integration of a handheld device with a ZED Mini depth sensor is explored
to produce Z-HandAR, a framework that enhances occlusion handling in handheld …

This paper introduces an autostereoscopic viewing method that eliminates the need for
specialized 3D glasses. The approach relies on vision-based motion parallax effects …

This paper introduces a novel approach to assist augmented reality (AR) research by
creating a versatile data-capturing rig and an integrated software pipeline. In this project we …