DDL-MVS: Depth Discontinuity Learning for Multi-View Stereo Networks

We propose an enhancement module called depth discontinuity learning (DDL) for learning-based multi-view stereo (MVS) methods. Traditional methods are known for their accuracy but struggle with completeness. While recent learning-based methods have improved completeness at the cost of accuracy, our DDL approach aims to improve accuracy while...

Reconstruction and Rendering of Buildings as Radiance Fields for View Synthesis

In inspection and display scenarios, reconstructing and rendering the entire surface of a building is a critical step in presenting the overall condition of the building. In building reconstruction, most works are based on point clouds because of their enhanced availability. In recent years, neural radiance fields (NeRF) have become a common...

Reconstructing compact building models from point clouds using deep implicit fields

While three-dimensional (3D) building models play an increasingly pivotal role in many real-world applications, obtaining a compact representation of buildings remains an open problem. In this paper, we present a novel framework for reconstructing compact, watertight, polygonal building models from point clouds. Our framework comprises three...

HRBF-Fusion: Accurate 3D Reconstruction from RGB-D Data Using On-the-fly Implicits

Reconstruction of high-fidelity 3D objects or scenes is a fundamental research problem. Recent advances in RGB-D fusion have demonstrated the potential of producing 3D models from consumer-level RGB-D cameras. However, due to the discrete nature and limited resolution of their surface representations (e.g., point or voxel based), existing...

Next-generation prognosis framework for pediatric spinal deformities using bio-informed deep learning networks

Predicting pediatric spinal deformity (PSD) from X-ray images collected on the patient’s initial visit is a challenging task. This work builds on our previous method and provides a novel bio-informed framework based on a mechanistic machine learning technique with dynamic patient-specific parameters to predict PSD. We provide a geometry-based...

Handling the unknown: Towards on-the-job object recognition

As robots are becoming a more integral part in our daily lives, it is important to ensure they work in a safe and efficient manner. A large part of perceiving the environment is done through robot vision. Research in computer vision and machine learning lead to great improvements in the past decades and robots are able to outperform humans on...

Learning to Reconstruct Compact Building Models from Point Clouds

Three-dimensional building models play a pivotal role in shaping the digital twin of our world. With the advance of sensing technologies, unprecedented data acquisition capabilities on capturing the built environment have surfaced, with photogrammetry and light detection and ranging being the two important sources, both of which can acquire...

Ground Truth for Evaluating 3D Reconstruction of Jet Engines

With 3D reconstruction from borescope videos of jet engines, inspections can be made more efficient. Being able to reconstruct 3D models of the jet engines potentially contributes to making the inspections autonomous. Methods that will be used for this reconstruction require to be evaluated to ensure the accuracy of the 3D models that they...

Fracture patterns in midshaft clavicle fractures

Current classifications of midshaft clavicle fractures are based on radiography. The aim of the study was to evaluate the fracture pattern of clavicle fractures using 3-dimensional computed tomography (3D CT). A retrospective analysis was performed on CT scans of 65 acute clavicle fractures. Using quantitative 3D CT reconstruction techniques,...

Point clouds to indoor/outdoor accessibility diagnosis

This work presents an approach to automatically detect structural floor elements such as steps or ramps in the immediate environment of buildings, elements that may affect the accessibility to buildings. The methodology is based on Mobile Laser Scanner (MLS) point cloud and trajectory information. First, the street is segmented in stretches...

Integration of 2D architectural floor plans into Indoor OpenStreetMap for reconstructing 3D building models

All existing data sources used to reconstruct 3D building models have certain restrictions. An eye-catching alternative is IndoorOSM, one of the most popular examples of the newly evolved crowdsourced geodata. The potential power of this rich and simple-formatted data source has been proven by many researches. However, a fatal flaw of IndoorOSM...

Architectural scene rapid reconstruction based on features

Retrieve the structure of model and the motion of camera is a classical and hot topic in computer vision and photogrammetry. A lot of automatic or semiautomatic techniques have been developed to optimize the retrieving processing from accuracy, stability and reality perspectives. These techniques are variant from data source, feature selection...