Using vanishing points for camera calibration and coarse 3D reconstruction from a single image

2000 ◽  
Vol 16 (7) ◽  
pp. 396-410 ◽  
Author(s):  
E Guillou ◽  
D. Meneveaux ◽  
E. Maisel ◽  
K. Bouatouch
Keyword(s):  
3D Reconstruction ◽  
Camera Calibration ◽  
Single Image ◽  
Vanishing Points

scholarly journals Jan van Eyck's Perspectival System Elucidated Through Computer Vision

2021 ◽  
Vol 4 (2) ◽  
pp. 1-8
Author(s):  
Gilles Simon
Keyword(s):  
Computer Vision ◽  
Augmented Reality ◽  
3D Reconstruction ◽  
Degrees Of Freedom ◽  
Human Vision ◽  
Vanishing Points ◽  
Two Degrees Of Freedom ◽  
Creative Media

It is generally accepted that Jan van Eyck was unaware of perspective. However, an a-contrario analysis of the vanishing points in five of his paintings, realized between 1432 and 1439, unveils a recurring fishbone-like pattern that could only emerge from the use of a polyscopic perspective machine with two degrees of freedom. A 3D reconstruction of Arnolfini Portrait compliant with this pattern suggests that van Eyck's device answered a both aesthetic and scientific questioning on how to represent space as closely as possible to human vision. This discovery makes van Eyck the father of today's immersive and nomadic creative media such as augmented reality and synthetic holography.

scholarly journals A 3D Reconstruction Framework of Buildings Using Single Off-Nadir Satellite Image

2021 ◽  
Vol 13 (21) ◽  
pp. 4434
Author(s):  
Chunhui Zhao ◽  
Chi Zhang ◽  
Yiming Yan ◽  
Nan Su
Keyword(s):  
Remote Sensing ◽  
3D Reconstruction ◽  
Spatial Resolution ◽  
Satellite Image ◽  
Geometric Constraints ◽  
Single Image ◽  
Multiple Images ◽  
Angle Size ◽  
Reconstruction Methods ◽  
Mesh Models

A novel framework for 3D reconstruction of buildings based on a single off-nadir satellite image is proposed in this paper. Compared with the traditional methods of reconstruction using multiple images in remote sensing, recovering 3D information that utilizes the single image can reduce the demands of reconstruction tasks from the perspective of input data. It solves the problem that multiple images suitable for traditional reconstruction methods cannot be acquired in some regions, where remote sensing resources are scarce. However, it is difficult to reconstruct a 3D model containing a complete shape and accurate scale from a single image. The geometric constraints are not sufficient as the view-angle, size of buildings, and spatial resolution of images are different among remote sensing images. To solve this problem, the reconstruction framework proposed consists of two convolutional neural networks: Scale-Occupancy-Network (Scale-ONet) and model scale optimization network (Optim-Net). Through reconstruction using the single off-nadir satellite image, Scale-Onet can generate water-tight mesh models with the exact shape and rough scale of buildings. Meanwhile, the Optim-Net can reduce the error of scale for these mesh models. Finally, the complete reconstructed scene is recovered by Model-Image matching. Profiting from well-designed networks, our framework has good robustness for different input images, with different view-angle, size of buildings, and spatial resolution. Experimental results show that an ideal reconstruction accuracy can be obtained both on the model shape and scale of buildings.

Quantitation of lower urinary tract afferents in 3D reconstruction of lumbosacral spinal cord sections v1

2021 ◽  
Author(s):  
John-Paul Fuller-Jackson ◽  
Peregrine B Osborne ◽  
Janet R Keast
Keyword(s):  
Spinal Cord ◽  
Urinary Tract ◽  
3D Reconstruction ◽  
Lower Urinary Tract ◽  
Single Image ◽  
Toxin B ◽  
Image Stack ◽  
Lumbosacral Spinal Cord ◽  
Cholera Toxin B ◽  
Lower Urinary

This protocol details the 3D reconstruction of the lumbosacral spinal cord using alternating cryosections, and then goes through the steps required to quantify lower urinary tract afferents. Using TissueMaker (MBF Bioscience), images of alternating sections can be ordered and aligned prior to the production of a single image stack. In Neurolucida 360 (MBF Bioscience), regions of interest can be defined within the image stack, and the bouton-like immunolabelling of cholera toxin B can be segmented. Once saved, this data can then be extracted using Neurolucida Explorer (MBF Bioscience).

Sign in / Sign up

Export Citation Format

Share Document