We contribute a large scale database for 3D object recognition, named ObjectNet3D, that consists of 100 categories, 90,127 images, 201,888 objects in these images and 44,147 3D shapes. Objects in the 2D images in our database are aligned with the 3D shapes, and the alignment provides both accurate 3D pose annotation and the closest 3D shape annotation for each 2D object. Consequently, our datab...

Introduction: 3D gradient echo (GRE) sequence is commonly used for T1-weighted MR imaging of liver. Conventional 3D GRE sequences utilize either one of centric-linear, radial or linear ordering of k-space with a fat suppression technique and partial scan technique along a slice direction. We introduce a enhanced 3D-GRE sequence, which adopted a linear ordering with half scan along both slice an...

We describe a computational method for depth extraction of three-dimensional (3D) objects using block matching for slice images in synthetic aperture integral imaging (SAII). SAII is capable of providing high-resolution 3D slice images for 3D objects because the picked-up elemental images are high-resolution ones. In the proposed method, the high-resolution elemental images are recorded by movi...

This paper addresses the problem of 3D human pose estimation in the wild. A significant challenge is the lack of training data, i.e., 2D images of humans annotated with 3D poses. Such data is necessary to train state-of-the-art CNN architectures. Here, we propose a solution to generate a large set of photorealistic synthetic images of humans with 3D pose annotations. We introduce an image-based...

BACKGROUND Abdominal computed tomography (CT) is a frequently performed imaging procedure, resulting in considerable radiation doses to the patient population. Postprocessing filters are one of several dose reduction measures that might help to reduce radiation doses without loss of image quality. PURPOSE To assess and compare the effect of two- and three-dimensional (2D, 3D) non-linear adapt...

In this paper, we present a recognition method for a 3D object in scattering media by using the axially distributed sensing (ADS) method and nonlinear correlation operation. Since the scatter noise for a 3D object is recorded into the elemental images by ADS method, we apply a statistical image-processing algorithm to convert the scattering elemental images into the scatter-reduced ones. After ...

BACKGROUND Recently, multi-planar reconstruction of the three-dimensional (3D) spiral chest CT scan has demonstrated superiority in the evaluation of the tracheobronchial tree. The goal of this study was to measure the lengths of the right and left main bronchi and their anteroposterior (AP) and transverse (TR) diameters using the 3D and two-dimensional (2D) images in the same adult respectivel...