Related papers: Cloud Tomography from Space using MISR and MODIS: …

Denoising diffusion models have demonstrated outstanding results in 2D image generation, yet it remains a challenge to replicate its success in 3D shape generation. In this paper, we propose leveraging multi-view depth, which represents…

In this paper, we review some of the properties of dense molecular cloud cores. The results presented here rely on three-dimensional numerical simulations of isothermal, magnetized, turbulent, and self-gravitating molecular clouds (MCs) in…

We study the rotational properties of magnetized and self-gravitating molecular cloud cores formed in 2 very high resolution 3D molecular cloud simulations.The simulations have been performed using the code RAMSES at an effective resolution…

3D object detection with LiDAR point clouds plays an important role in autonomous driving perception module that requires high speed, stability and accuracy. However, the existing point-based methods are challenging to reach the speed…

This study introduces a method for efficiently detecting objects within 3D point clouds using convolutional neural networks (CNNs). Our approach adopts a unique feature-centric voting mechanism to construct convolutional layers that…

3D tomography of the interstellar dust and gas may be useful in many respects, from the physical and chemical evolution of the ISM itself to foreground decontamination of the CMB, or various studies of the environments of specific objects.…

Point clouds are a very efficient way to represent volumetric data in medical imaging. First, they do not occupy resources for empty spaces and therefore can avoid trade-offs between resolution and field-of-view for voxel-based 3D…

We demonstrate a motion-free intensity diffraction tomography technique that enables direct inversion of 3D phase and absorption from intensity-only measurements for weakly scattering samples. We derive a novel linear forward model,…

Three-dimensional (3D) kinetic maps of the Milky Way interstellar medium are an essential tool in studies of its structure and of star formation. We aim to assign radial velocities to Galactic interstellar clouds now spatially localized…

3D object detection and dense depth estimation are one of the most vital tasks in autonomous driving. Multiple sensor modalities can jointly attribute towards better robot perception, and to that end, we introduce a method for jointly…

The emerging technique of mid-infrared optical coherence tomography (MIR-OCT) takes advantage of the reduced scattering of MIR light in various materials and devices, enabling tomographic imaging at deeper penetration depths. Because of…

We propose Concavity-induced Distance (CID) as a novel way to measure the dissimilarity between a pair of points in an unoriented point cloud. CID indicates the likelihood of two points or two sets of points belonging to different convex…

We present the first degree-scale tomography map of the dusty magnetized interstellar medium (ISM) from stellar polarimetry and distance measurements. We used the RoboPol polarimeter at Skinakas Observatory to conduct a survey of starlight…

In recent years considerable research in LiDAR semantic segmentation was conducted, introducing several new state of the art models. However, most research focuses on single-scan point clouds, limiting performance especially in long…

Semantic segmentation of raw 3D point clouds is an essential component in 3D scene analysis, but it poses several challenges, primarily due to the non-Euclidean nature of 3D point clouds. Although, several deep learning based approaches…

Efficient representation of point clouds is fundamental for LiDAR-based 3D object detection. While recent grid-based detectors often encode point clouds into either voxels or pillars, the distinctions between these approaches remain…

Cross-modal 3D retrieval is a critical yet challenging task, aiming to achieve bi-directional retrieval between 3D and text modalities. Current methods predominantly rely on a certain 3D representation (e.g., point cloud), with few…

Point clouds captured by scanning devices are often incomplete due to occlusion. To overcome this limitation, point cloud completion methods have been developed to predict the complete shape of an object based on its partial input. These…

Natural (such as lunar) occultations have long been used to study sources on small angular scales, while coronographs have been used to study high contrast sources. We propose launching the Improved Resolution and Image Selection (IRIS)…

Semantic segmentation by convolutional neural networks (CNN) has advanced the state of the art in pixel-level classification of remote sensing images. However, processing large images typically requires analyzing the image in small patches,…