Related papers: DNN-based 3D Cloud Retrieval for Variable Solar Il…
We propose Shift R-CNN, a hybrid model for monocular 3D object detection, which combines deep learning with the power of geometry. We adapt a Faster R-CNN network for regressing initial 2D and 3D object properties and combine it with a…
Existing deep neural network (DNN) based wireless localization approaches typically do not capture uncertainty inherent in their estimates. In this work, we propose and evaluate variational and scalable DNN approaches to measure the…
We address the essential role of information retrieval in enhancing climate downscaling, focusing on the need for high-resolution datasets and the application of deep learning models. We explore the requirements for acquiring detailed…
3D object detection with multi-sensors is essential for an accurate and reliable perception system of autonomous driving and robotics. Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm which merely…
Coherent imaging through scatter is a challenging task in computational imaging. Both model-based and data-driven approaches have been explored to solve the inverse scattering problem. In our previous work, we have shown that a deep…
Methods of three-dimensional deconvolution (3DD) or volumetric deconvolution of optical complex-valued wavefronts diffracted by 3D samples with the 3D point spread function are presented. Particularly, the quantitative correctness of the…
We develop a hybrid GNN-CNN architecture for the reconstruction of 3-dimensional continuous cosmological matter fields from discrete point clouds, provided by observed galaxy catalogs. Using the CAMELS hydrodynamical cosmological…
As an emerging data modal with precise distance sensing, LiDAR point clouds have been placed great expectations on 3D scene understanding. However, point clouds are always sparsely distributed in the 3D space, and with unstructured storage,…
Rain degrades the visual quality of multi-view images, which are essential for 3D scene reconstruction, resulting in inaccurate and incomplete reconstruction results. Existing datasets often overlook two critical characteristics of real…
In order to retrieve cosmological parameters from photometric surveys, we need to estimate the distribution of the photometric redshift in the sky with excellent accuracy. We use and apply three different machine learning methods to…
The recent advances in 3D sensing technology have made possible the capture of point clouds in significantly high resolution. However, increased detail usually comes at the expense of high storage, as well as computational costs in terms of…
Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image…
We present 3DeepCT, a deep neural network for computed tomography, which performs 3D reconstruction of scattering volumes from multi-view images. Our architecture is dictated by the stationary nature of atmospheric cloud fields. The task of…
We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D geometry to fuse input images into…
In recent years, deep neural networks (DNNs) have gained widespread adoption for continuous mobile object detection (OD) tasks, particularly in autonomous systems. However, a prevalent issue in their deployment is the one-size-fits-all…
Digital elevation modeling of planetary surfaces is essential for studying past and ongoing geological processes. Wide-angle imagery acquired during spacecraft descent promises to offer a low-cost option for high-resolution terrain…
The emergence of a new discipline called space weather, which aims at understanding and predicting the impact of solar activity on the terrestrial environment and on technological systems, has led to a growing need for analysing solar…
Weather Recognition plays an important role in our daily lives and many computer vision applications. However, recognizing the weather conditions from a single image remains challenging and has not been studied thoroughly. Generally, most…
The increasingly populated cities of the 21st Century face the challenge of being sustainable and resilient spaces for their inhabitants. However, climate change, among other problems, makes these objectives difficult to achieve. The Urban…
Distribution-to-distribution (D2D) point cloud registration techniques such as the Normal Distributions Transform (NDT) can align point clouds sampled from unstructured scenes and provide accurate bounds of their own solution error…