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

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 …

In this paper, we propose a deep learning architecture that produces accurate dense depth
for the outdoor scene from a single color image and a sparse depth. Inspired by the indoor …

We propose DeepHuman, an image-guided volume-to-volume translation CNN for 3D
human reconstruction from a single RGB image. To reduce the ambiguities associated with …

We present" The Relightables", a volumetric capture system for photorealistic and high
quality relightable full-body performance capture. While significant progress has been made …

This paper presents StereoNet, the first end-to-end deep architecture for real-time stereo
matching that runs at 60 fps on an NVidia Titan X, producing high-quality, edge-preserved …

We propose DiffuStereo, a novel system using only sparse cameras (8 in this work) for high-
quality 3D human reconstruction. At its core is a novel diffusion-based stereo module, which …

The modulation and projection of patterns are the cornerstones of spatially structured-light
three-dimensional (3D) imaging. However, an overview of this field is lacking. This paper …

Polarization imaging can retrieve inaccurate objects' 3D shapes with fine textures, whereas
coarse but accurate depths can be provided by binocular stereo vision. To take full …

We present Motion2Fusion, a state-of-the-art 360 performance capture system that enables*
real-time* reconstruction of arbitrary non-rigid scenes. We provide three major contributions …