Related papers: A differentiable and optimizable 3D model for inte…

We describe a pseudo-3D photoionization code, NEBU_3D and its associated visualization tool, VIS_NEB3D, which are able to easily and rapidly treat a wide variety of nebular geometries, by combining models obtained with a 1D photoionization…

LIDAR 3D object detection is one of the important tasks for autonomous vehicles. Ensuring that this task operates in real-time is crucial. Toward this, model quantization can be used to accelerate the runtime. However, directly applying…

Unlike vision and language data which usually has a unique format, molecules can naturally be characterized using different chemical formulations. One can view a molecule as a 2D graph or define it as a collection of atoms located in a 3D…

The ability to interpret machine learning model decisions is critical in such domains as healthcare, where trust in model predictions is as important as their accuracy. Inspired by the development of prototype parts-based deep neural…

Many analyses in particle and nuclear physics use simulations to infer fundamental, effective, or phenomenological parameters of the underlying physics models. When the inference is performed with unfolded cross sections, the observables…

Conventional methods of 3D object generative modeling learn volumetric predictions using deep networks with 3D convolutional operations, which are direct analogies to classical 2D ones. However, these methods are computationally wasteful in…

Context. The deuterium fraction in low-mass prestellar cores is a good diagnostic indicator of the initial phases of star formations, and it is also a fundamental quantity to infer the ionisation degree in these objects. Aims. With the…

We present PI3DETR, an end-to-end framework that directly predicts 3D parametric curve instances from raw point clouds, avoiding the intermediate representations and multi-stage processing common in prior work. Extending 3DETR, our model…

The intrinsically hierarchical and blended structure of interstellar molecular clouds, plus the always increasing resolution of astronomical instruments, demand advanced and automated pattern recognition techniques for identifying and…

Machine learning models can assist with metamaterials design by approximating computationally expensive simulators or solving inverse design problems. However, past work has usually relied on black box deep neural networks, whose reasoning…

Water is an important molecule in the chemical and thermal balance of dense molecular gas, but knowing its history through-out the various stages of the star formation is a fundamental problem. Its molecular deuteration provides us with a…

Generative models have achieved impressive results in many domains including image and text generation. In the natural sciences, generative models have led to rapid progress in automated drug discovery. Many of the current methods focus on…

We represent 3D shape by structured 2D representations of fixed length making it feasible to apply well investigated 2D convolutional neural networks (CNN) for both discriminative and geometric tasks on 3D shapes. We first provide a general…

We present 2D Monte Carlo radiative transfer simulations of prestellar cores. We consider two types of asymmetry: disk-like asymmetry, in which the core is denser towards the equatorial plane than towards the poles; and axial asymmetry, in…

A novel, adaptive ground-aware, and cost-effective 3D Object Detection pipeline is proposed. The ground surface representation introduced in this paper, in comparison to its uni-planar counterparts (methods that model the surface of a whole…

Modeling sequential patterns from data is at the core of various time series forecasting tasks. Deep learning models have greatly outperformed many traditional models, but these black-box models generally lack explainability in prediction…

Modeling the dynamics of deformable objects is challenging due to their diverse physical properties and the difficulty of estimating states from limited visual information. We address these challenges with a neural dynamics framework that…

We propose PyTorchGeoNodes, a differentiable module for reconstructing 3D objects and their parameters from images using interpretable shape programs. Unlike traditional CAD model retrieval, shape programs allow reasoning about semantic…

This paper presents a compact and accurate representation of 3D scenes that are observed by a LiDAR sensor and a monocular camera. The proposed method is based on the well-established Stixel model originally developed for stereo vision…

LiDAR point clouds are widely used in autonomous driving and consist of large numbers of 3D points captured at high frequency to represent surrounding objects such as vehicles, pedestrians, and traffic signs. While this dense data enables…