中文
相关论文

相关论文: Hyperspectral recovery from RGB images using Gauss…

200 篇论文

To train a deblurring network, an appropriate dataset with paired blurry and sharp images is essential. Existing datasets collect blurry images either synthetically by aggregating consecutive sharp frames or using sophisticated camera…

计算机视觉与模式识别 · 计算机科学 2024-11-01 Dongwoo Lee , Joonkyu Park , Kyoung Mu Lee

While 3D Gaussian Splatting (3D-GS) achieves photorealistic novel view synthesis, its performance degrades with motion blur. In scenarios with rapid motion or low-light conditions, existing RGB-based deblurring methods struggle to model…

计算机视觉与模式识别 · 计算机科学 2025-07-14 Yufei Deng , Yuanjian Wang , Rong Xiao , Chenwei Tang , Jizhe Zhou , Jiahao Fan , Deng Xiong , Jiancheng Lv , Huajin Tang

In this paper, we study random subsampling of Gaussian process regression, one of the simplest approximation baselines, from a theoretical perspective. Although subsampling discards a large part of training data, we show provable guarantees…

机器学习 · 统计学 2019-01-29 Kohei Hayashi , Masaaki Imaizumi , Yuichi Yoshida

Hyperspectral imagery (HSI) is an established technique with an array of applications, but its use is limited due to both practical and technical issues associated with spectral devices. The goal of the ICASSP 2024 'Hyper-Skin' Challenge is…

图像与视频处理 · 电气工程与系统科学 2024-04-17 Wojciech Czaja , Jeremiah Emidih , Brandon Kolstoe , Richard G. Spencer

While neural rendering has demonstrated impressive capabilities in 3D scene reconstruction and novel view synthesis, it heavily relies on high-quality sharp images and accurate camera poses. Numerous approaches have been proposed to train…

计算机视觉与模式识别 · 计算机科学 2024-03-20 Lingzhe Zhao , Peng Wang , Peidong Liu

Gaussian processes are powerful models for probabilistic machine learning, but are limited in application by their $O(N^3)$ inference complexity. We propose a method for deriving parametric families of kernel functions with compact spatial…

机器学习 · 计算机科学 2020-06-09 Jarred Barber

We describe a novel method for blind, single-image spectral super-resolution. While conventional super-resolution aims to increase the spatial resolution of an input image, our goal is to spectrally enhance the input, i.e., generate an…

计算机视觉与模式识别 · 计算机科学 2017-03-29 Silvano Galliani , Charis Lanaras , Dimitrios Marmanis , Emmanuel Baltsavias , Konrad Schindler

Single-pixel imaging (SPI) offers a cost-effective route to hyperspectral acquisition but struggles to recover high-fidelity spatial and spectral details under extremely low sampling rates, a severely ill-posed inverse problem. While deep…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Hao Zhang , Bilige Xu , Lichen Wei , Xu Ma , Wenyi Ren

Inference in popular nonparametric Bayesian models typically relies on sampling or other approximations. This paper presents a general methodology for constructing novel tractable nonparametric Bayesian methods by applying the kernel trick…

机器学习 · 统计学 2011-08-15 Ferenc Huszár , Simon Lacoste-Julien

The cost-effectiveness and practical harmlessness of ultrasound imaging have made it one of the most widespread tools for medical diagnosis. Unfortunately, the beam-forming based image formation produces granular speckle noise, blurring,…

计算机视觉与模式识别 · 计算机科学 2017-10-19 Sanketh Vedula , Ortal Senouf , Alex M. Bronstein , Oleg V. Michailovich , Michael Zibulevsky

We propose a novel class of Gaussian processes (GPs) whose spectra have compact support, meaning that their sample trajectories are almost-surely band limited. As a complement to the growing literature on spectral design of covariance…

机器学习 · 统计学 2019-09-17 Felipe Tobar

This paper proposes a general framework for internal patch-based image restoration based on Conditional Random Fields (CRF). Unlike related models based on Markov Random Fields (MRF), our approach explicitly formulates the posterior…

计算机视觉与模式识别 · 计算机科学 2018-07-10 Milad Niknejad , Jose M. Bioucas-Dias , Mario A. T. Figueiredo

Hyperspectral imaging provides detailed information about the scanned objects, as it captures their spectral characteristics within a large number of wavelength bands. Classification of such data has become an active research topic due to…

计算机视觉与模式识别 · 计算机科学 2019-07-30 Jakub Nalepa , Lukasz Tulczyjew , Michal Myller , Michal Kawulok

Gaussian processes (GPs) are an attractive class of machine learning models because of their simplicity and flexibility as building blocks of more complex Bayesian models. Meanwhile, graph neural networks (GNNs) emerged recently as a…

机器学习 · 计算机科学 2023-02-14 Zehao Niu , Mihai Anitescu , Jie Chen

Bayesian inference of nanohertz gravitational-wave background models in pulsar timing array analyses often relies on Gaussian-process interpolators to avoid repeated, computationally expensive strain-spectrum calculations. However,…

宇宙学与河外天体物理 · 物理学 2026-04-16 Shreyas Tiruvaskar , Chris Gordon

Gaussian boson sampling (GBS) has emerged as a promising quantum computing paradigm, demonstrating its potential in various applications. However, most existing works focus on theoretical aspects or simple tasks, with limited exploration of…

Recovering the radiometric properties of a scene (i.e., the reflectance, illumination, and geometry) is a long-sought ability of computer vision that can provide invaluable information for a wide range of applications. Deciphering the…

计算机视觉与模式识别 · 计算机科学 2016-04-06 Stephen Lombardi , Ko Nishino

Recently, impressive denoising results have been achieved by Bayesian approaches which assume Gaussian models for the image patches. This improvement in performance can be attributed to the use of per-patch models. Unfortunately such an…

计算机视觉与模式识别 · 计算机科学 2017-12-08 Cecilia Aguerrebere , Andrés Almansa , Julie Delon , Yann Gousseau , Pablo Musé

The use of Gaussian processes (GPs) is a common approach to account for correlated noise in exoplanet time series, particularly for transmission and emission spectroscopy. This analysis has typically been performed for each wavelength…

地球与行星天体物理 · 物理学 2024-06-05 Mark Fortune , Neale P. Gibson , Daniel Foreman-Mackey , Thomas M. Evans-Soma , Cathal Maguire , Swaetha Ramkumar

Hyper-spectral data can be analyzed to recover physical properties at large planetary scales. This involves resolving inverse problems which can be addressed within machine learning, with the advantage that, once a relationship between…

应用统计 · 统计学 2015-12-31 Antoine Deleforge , Florence Forbes , Sileye Ba , Radu Horaud