Image segmentation refers to the process to divide an image into meaningful non-
overlap** regions according to human perception, which has become a classic topic since …

This paper presents HITNet, a novel neural network architecture for real-time stereo
matching. Contrary to many recent neural network approaches that operate on a full …

Abstract FlowNet2, the state-of-the-art convolutional neural network (CNN) for optical flow
estimation, requires over 160M parameters to achieve accurate flow estimation. In this paper …

Our goal is to significantly speed up the runtime of current state-of-the-art stereo algorithms
to enable real-time inference. Towards this goal, we developed a differentiable PatchMatch …

Superpixels group perceptually similar pixels to create visually meaningful entities while
heavily reducing the number of primitives for subsequent processing steps. As of these …

We present a novel algorithm for view synthesis that utilizes a soft 3D reconstruction to
improve quality, continuity and robustness. Our main contribution is the formulation of a soft …

Superpixels provide an efficient low/mid-level representation of image data, which greatly
reduces the number of image primitives for subsequent vision tasks. Existing superpixel …

Over four decades, the majority addresses the problem of optical flow estimation using
variational methods. With the advance of machine learning, some recent works have …

Wireless sensor networks are composed of large numbers of tiny networked devices that
communicate untethered. For large scale networks, it is important to be able to download …

This paper presents a coherent framework for automated unmanned aircraft system based
inspections of large bridges to facilitate an automated condition assessment. Modern …