With the advances in scientific foundations and technological implementations, optical
metrology has become versatile problem-solving backbones in manufacturing, fundamental …

Stereo matching is one of the longest-standing problems in computer vision with close to 40
years of studies and research. Throughout the years the paradigm has shifted from local …

Stereo matching is a fundamental building block for many vision and robotics applications.
An informative and concise cost volume representation is vital for stereo matching of high …

Despite the remarkable progress made by learning based stereo matching algorithms, one
key challenge remains unsolved. Current state-of-the-art stereo models are mostly based on …

Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in
machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a …

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 …

Estimating depth from RGB images is a long-standing ill-posed problem, which has been
explored for decades by the computer vision, graphics, and machine learning communities …

We present an end-to-end 3D reconstruction method for a scene by directly regressing a
truncated signed distance function (TSDF) from a set of posed RGB images. Traditional …

We propose a novel end-to-end deep scene flow model, called PointPWC-Net, that directly
processes 3D point cloud scenes with large motions in a coarse-to-fine fashion. Flow …

The majority of prior monocular depth estimation methods without groundtruth depth
guidance focus on driving scenarios. We show that such methods generalize poorly to …