Related papers: Cloud Tomography from Space using MISR and MODIS: …
At present, the anchor-based or anchor-free models that use LiDAR point clouds for 3D object detection use the center assigner strategy to infer the 3D bounding boxes. However, in a real world scene, the LiDAR can only acquire a limited…
Automatic extraction of road curbs from uneven, unorganized, noisy and massive 3D point clouds is a challenging task. Existing methods often project 3D point clouds onto 2D planes to extract curbs. However, the projection causes loss of 3D…
Astronomers have used observations of the Galactic gas and dust via infrared, microwave, and radio to study molecular clouds in extreme environments such as the Galactic center. More recently, X- ray telescopes have opened up a new…
Sky/cloud images obtained from ground-based sky-cameras are usually captured using a fish-eye lens with a wide field of view. However, the sky exhibits a large dynamic range in terms of luminance, more than a conventional camera can…
Remarkable progress has been made in self-supervised monocular depth estimation (SS-MDE) by exploring cross-view consistency, e.g., photometric consistency and 3D point cloud consistency. However, they are very vulnerable to illumination…
As one of the basic tasks of computer vision, object detection has been widely used in many intelligent applications. However, object detection algorithms are usually heavyweight in computation, hindering their implementations on…
Point cloud compression plays a crucial role in reducing the huge cost of data storage and transmission. However, distortions can be introduced into the decompressed point clouds due to quantization. In this paper, we propose a novel…
Multimode fibers recently emerged as compact minimally-invasive probes for high-resolution deep-tissue imaging. However, the commonly used silica fibers have a relatively low numerical aperture (NA) limiting the spatial resolution of a…
Unified schemes of active galactic nuclei (AGN) require an obscuring dusty torus around the central source, giving rise to type 1 line spectrum for pole-on viewing and type 2 characteristics in edge-on sources. Infrared radiation at its…
We have constructed three-dimensional models for the equilibrium abundance of molecular hydrogen within diffuse interstellar clouds of arbitrary geometry that are illuminated by ultraviolet radiation. The position-dependent photo-…
We study the properties of giant molecular clouds (GMCs) from a smoothed particle hydrodynamics simulation of a portion of a spiral galaxy, modelled at high resolution, with robust representations of the physics of the interstellar medium.…
Deep learning has been recently applied to a multitude of computer vision and medical image analysis problems. Although recent research efforts have improved the state of the art, most of the methods cannot be easily accessed, compared or…
Molecular clouds are observed to be turbulent, but the origin of this turbulence is not well understood. As a result, there are two different approaches to simulating molecular clouds, one in which the turbulence is allowed to decay after…
The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and…
Visual localization is the problem of estimating the camera pose of a given image with respect to a known scene. Visual localization algorithms are a fundamental building block in advanced computer vision applications, including Mixed and…
Autonomous vehicles rely on LiDAR sensors to generate 3D point clouds for accurate segmentation and object detection. In a context of a smart city framework, we would like to understand the effect that transmission (compression) can have on…
Observations are revealing the ubiquity of filamentary structures in molecular clouds. As cores are often embedded in filaments, it is important to understand how line profiles from such systems differ from those of isolated cores. We…
This paper reports a new continuous 3D loss function for learning depth from monocular images. The dense depth prediction from a monocular image is supervised using sparse LIDAR points, which enables us to leverage available open source…
We present a catalogue of molecular cloud cores drawn from high latitude, medium opacity clouds, using the all-sky IRAS Sky Survey Atlas (ISSA) images at 60 and 100~$\mu$m. The typical column densities of the cores are $ N(H_2)\sim 3.8…
We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud (rendered as depth images). Prior works were demonstrated on…