中文
相关论文

相关论文: Streaming Gaussian Dirichlet Random Fields for Spa…

200 篇论文

We present GP-4DGS, a novel framework that integrates Gaussian Processes (GPs) into 4D Gaussian Splatting (4DGS) for principled probabilistic modeling of dynamic scenes. While existing 4DGS methods focus on deterministic reconstruction,…

计算机视觉与模式识别 · 计算机科学 2026-04-06 Mijeong Kim , Jungtaek Kim , Bohyung Han

The difficulty of monitoring biodiversity at fine scales and over large areas limits ecological knowledge and conservation efforts. To fill this gap, Species Distribution Models (SDMs) predict species across space from spatially explicit…

The streaming model describes the mapping between real and redshift space for 2-point clustering statistics. Its key element is the probability density function (PDF) of line-of-sight pairwise peculiar velocities. Following a kinetic-theory…

宇宙学与河外天体物理 · 物理学 2018-07-24 Joseph Kuruvilla , Cristiano Porciani

Streamflow is a dynamical process that integrates water movement in space and time within basin boundaries. The authors characterize the dynamics associated with streamflow time series data from about seventy-one U.S. Geological Survey…

物理与社会 · 物理学 2021-04-14 Ganesh R. Ghimire , Navid Jadidoleslam , Witold F. Krajewski , Anastasios A. Tsonis

Gaussian random field (GRF) models are widely used in spatial statistics to capture spatially correlated error. We investigate the results of replacing Gaussian processes with Laplace moving averages (LMAs) in spatial generalized linear…

应用统计 · 统计学 2019-07-26 Adam Walder , Ephraim M. Hanks

Individual trajectories, rich in human-environment interaction information across space and time, serve as vital inputs for geospatial foundation models (GeoFMs). However, existing attempts at learning trajectory representations have…

机器学习 · 计算机科学 2025-05-13 Fei Huang , Jianrong Lv , Yang Yue

3D Gaussian Splatting has emerged as a powerful approach in novel view synthesis, delivering rapid training and rendering but at the cost of an ever-growing set of Gaussian primitives that strains memory and bandwidth. We introduce…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Hung Nguyen , An Le , Runfa Li , Truong Nguyen

Robot motion distributions often exhibit multi-modality and require flexible generative models for accurate representation. Streaming Flow Policies (SFPs) have recently emerged as a powerful paradigm for generating robot trajectories by…

机器人学 · 计算机科学 2026-02-18 Jieting Long , Dechuan Liu , Weidong Cai , Ian Manchester , Weiming Zhi

Recently, Gaussian splatting has emerged as a strong alternative to NeRF, demonstrating impressive 3D modeling capabilities while requiring only a fraction of the training and rendering time. In this paper, we show how the standard Gaussian…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Luca Savant Aira , Gabriele Facciolo , Thibaud Ehret

Accurate predictions of spatio-temporal systems are crucial for tasks such as system management, control, and crisis prevention. However, the inherent time variance of many spatio-temporal systems poses challenges to achieving accurate…

机器学习 · 计算机科学 2025-07-14 Xiaobei Zou , Luolin Xiong , Kexuan Zhang , Cesare Alippi , Yang Tang

Deep learning approaches for spatio-temporal prediction problems such as crowd-flow prediction assumes data to be of fixed and regular shaped tensor and face challenges of handling irregular, sparse data tensor. This poses limitations in…

机器学习 · 计算机科学 2022-11-29 Syed Mohammed Arshad Zaidi , Varun Chandola , EunHye Yoo

Referring 3D Gaussian Splatting Segmentation (R3DGS) aims to ground free-form language queries in 3D Gaussian fields. However, existing methods rely on single-view pseudo supervision, leading to viewpoint drift and inconsistent predictions…

计算机视觉与模式识别 · 计算机科学 2026-03-23 Yuwen Tao , Kanglei Zhou , Xin Tan , Yuan Xie

Sampling from Gaussian Markov random fields (GMRFs), that is multivariate Gaussian ran- dom vectors that are parameterised by the inverse of their covariance matrix, is a fundamental problem in computational statistics. In this paper, we…

A spike camera is a specialized high-speed visual sensor that offers advantages such as high temporal resolution and high dynamic range compared to conventional frame cameras. These features provide the camera with significant advantages in…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Jinze Yu , Xin Peng , Zhengda Lu , Laurent Kneip , Yiqun Wang

Stochastic Gumbel graph networks are proposed to learn high-dimensional time series, where the observed dimensions are often spatially correlated. To that end, the observed randomness and spatial-correlations are captured by learning the…

机器学习 · 计算机科学 2023-07-13 Jin Guo , Ting Gao , Yufu Lan , Peng Zhang , Sikun Yang , Jinqiao Duan

Spatiotemporal datasets, which consist of spatially-referenced time series, are ubiquitous in diverse applications, such as air pollution monitoring, disease tracking, and cloud-demand forecasting. As the scale of modern datasets increases,…

机器学习 · 计算机科学 2024-11-28 Feras Saad , Jacob Burnim , Colin Carroll , Brian Patton , Urs Köster , Rif A. Saurous , Matthew Hoffman

We propose the novel augmented Gaussian random field (AGRF), which is a universal framework incorporating the data of observable and derivatives of any order. Rigorous theory is established. We prove that under certain conditions, the…

统计理论 · 数学 2021-11-30 Sheng Zhang , Xiu Yang , Samy Tindel , Guang Lin

Autonomous robots are increasingly deployed to estimate spatiotemporal fields (e.g., wind, temperature, gas concentration) that vary across space and time. We consider environments divided into non-overlapping regions with distinct spatial…

机器人学 · 计算机科学 2025-09-30 Kaleb Ben Naveed , Haejoon Lee , Dimitra Panagou

Weather Forecasting is an attractive challengeable task due to its influence on human life and complexity in atmospheric motion. Supported by massive historical observed time series data, the task is suitable for data-driven approaches,…

机器学习 · 计算机科学 2022-09-20 Minbo Ma , Peng Xie , Fei Teng , Tianrui Li , Bin Wang , Shenggong Ji , Junbo Zhang

In this paper, we propose a randomized generalized multiscale finite element method (Randomized GMsFEM) for flow problems with parameterized inputs and high-contrast heterogeneous media. The method employs a data-driven predictor to…

数值分析 · 数学 2025-08-05 Wing Tat Leung , Qiuqi Li , Songwei Liu