Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

State-of-the-art automated image orientation (Structure from Motion) and dense image
matching (Multiple View Stereo) methods commonly used to produce 3D information from …

We present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for
high-resolution multi-view stereo. With high computation speed and low memory …

This paper introduces the Meshroom software and its underlying 3D computer vision
framework AliceVision. This solution provides a photogrammetry pipeline to reconstruct 3D …

We present an end-to-end deep learning architecture for depth map inference from multi-
view images. In the network, we first extract deep visual image features, and then build the …

With the pervasive use of Building Information Modelling (BIM), lean principles, digital
technologies, and offsite construction, the industry is at the cusp of this transformation. The …

We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo
reconstruction. Taking an arbitrary number of posed images as input, we first produce a set …

This paper describes how to obtain accurate 3D body models and texture of arbitrary people
from a single, monocular video in which a person is moving. Based on a parametric body …

In this paper we formulate structure from motion as a learning problem. We train a
convolutional network end-to-end to compute depth and camera motion from successive …

Learning-based methods are demonstrating their strong competitiveness in estimating depth
for multi-view stereo reconstruction in recent years. Among them the approaches that …