For the use of 6D pose estimation in robotic applications, reliable poses are of utmost importance to ensure a safe, reliable and predictable operational performance. Despite these requirements, state-of-the-art 6D pose estimators often do not provide any uncertainty quantification for their pose estimates at all, or if they do, it has been shown that the uncertainty provided is only weakly correlated with the actual true error. To address this issue, we investigate a simple but effective uncertainty quantification, that we call MaskVal, which compares the pose estimates with their corresponding instance segmentations by rendering and does not require any modification of the pose estimator itself. Despite its simplicity, MaskVal significantly outperforms a state-of-the-art ensemble method on both a dataset and a robotic setup. We show that by using MaskVal, the performance of a state-of-the-art 6D pose estimator is significantly improved towards a safe and reliable operation. In addition, we propose a new and specific approach to compare and evaluate uncertainty quantification methods for 6D pose estimation in the context of robotic manipulation.
NVIDIA（英伟达）；California Institute of Technology（加州理工学院）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；The University of Sydney（悉尼大学）
Deep learning-based object pose estimators are often unreliable and overconfident especially when the input image is outside the training domain, for instance, with sim2real transfer. Efficient and robust uncertainty quantification (UQ) in pose estimators is critically needed in many robotic tasks. In this work, we propose a simple, efficient, and plug-and-play UQ method for 6-DoF object pose estimation. We ensemble 2-3 pre-trained models with different neural network architectures and/or training data sources, and compute their average pairwise disagreement against one another to obtain the u…
A Critical Synthesis of Uncertainty Quantification and Foundation Models in Monocular Depth Estimation
Institute of Photogrammetry and Remote Sensing (IPF), Karlsruhe Institute of Technology (KIT)（摄影测量与遥感研究所（卡尔斯鲁厄理工学院））；The Ohio State University（俄亥俄州立大学）
University of Notre Dame（圣母大学）；Technical University of Munich（慕尼黑工业大学）；University of Pennsylvania（宾夕法尼亚大学）
Surrogate modeling and uncertainty quantification tasks for PDE systems are most often considered as supervised learning problems where input and output data pairs are used for training. The construction of such emulators is by definition a small data problem which poses challenges to deep learning approaches that have been developed to operate in the big data regime. Even in cases where such models have been shown to have good predictive capability in high dimensions, they fail to address constraints in the data implied by the PDE model. This paper provides a methodology that incorporates the…
Seismic imaging is an ill-posed inverse problem that is challenged by noisy data and modeling inaccuracies -- due to errors in the background squared-slowness model. Uncertainty quantification is essential for determining how variability in the background models affects seismic imaging. Due to the costs associated with the forward Born modeling operator as well as the high dimensionality of seismic images, quantification of uncertainty is computationally expensive. As such, the main contribution of this work is a survey-specific Fourier neural operator surrogate to velocity continuation that m…
We propose a novel \textit{capsule} based deep encoder-decoder model for surrogate modeling and uncertainty quantification of systems in mechanics from sparse data. The proposed framework is developed by adapting Capsule Network (CapsNet) architecture into image-to-image regression encoder-decoder network. Specifically, the aim is to exploit the benefits of CapsNet over convolution neural network (CNN) $-$ retaining pose and position information related to an entity to name a few. The performance of proposed approach is illustrated by solving an elliptic stochastic partial differential equatio…
Micro-Macro Tensor Neural Surrogates for Uncertainty Quantification in Collisional Plasma
University of Ferrara（费拉拉大学）；Italian Ministry of University and Research（意大利大学与研究部）；Royal Society（皇家学会）；Italian National Institute of High Mathematics（意大利高等数学研究院）
German Cancer Research Center（德国癌症研究中心）；Heidelberg University（海德堡大学）；University of Bern（伯尔尼大学）
Multispectral photoacoustic imaging (PAI) is an emerging imaging modality which enables the recovery of functional tissue parameters such as blood oxygenation. However, the underlying inverse problems are potentially ill-posed, meaning that radically different tissue properties may - in theory - yield comparable measurements. In this work, we present a new approach for handling this specific type of uncertainty by leveraging the concept of conditional invertible neural networks (cINNs). Specifically, we propose going beyond commonly used point estimates for tissue oxygenation and converting si…
Microstructure-based Variational Neural Networks for Robust Uncertainty Quantification in Materials Digital Twins
Center for Integrated Nanotechnologies（集成纳米技术中心）；Sandia National Laboratories（桑塔纳国家实验室）；Theoretical Division（理论 division）；Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Department of Mechanical Engineering（机械工程系）；Pohang University of Science and Technology（釜山科学技术大学）
Counterfactual Uncertainty Quantification of Factual Estimand of Efficacy from Before-and-After Treatment Repeated Measures Randomized Controlled Trials
Department of Mathematics, The University of Manchester；Janssen Research；Pfizer Worldwide Research \& Development；Department of Statistics, The Ohio State University
Structure and asymptotic preserving deep neural surrogates for uncertainty quantification in multiscale kinetic equations
University of Ferrara（费拉拉大学）；Italian Ministry of University and Research（意大利大学与研究部）；Royal Society（皇家学会）；European Union（欧盟）；ICSC – Centro Nazionale di Ricerca in High Performance Computing, Big Data and Quantum Computing（ICSC – 高性能计算、大数据和量子计算研究中心）；Italian National Institute of High Mathematics（意大利国家高等数学研究所）
Uncertainty Quantification in PINNs for Turbulent Flows: Bayesian Inference and Repulsive Ensembles
Division of Applied Mathematics, Brown University（布朗大学应用数学系）；Department of Computing and Mathematical Sciences, California Institute of Technology（加州理工学院计算与数学科学系）；Department of Mechanical Engineering, Massachusetts Institute of Technology（麻省理工学院机械工程系）
本文提出了一种概率扩展的PINN框架，结合贝叶斯方法、麦克斯韦-玻尔兹曼抽样和斥力深度集合，以提高湍流建模中的不确定性校准，通过Van der Pol振荡器和圆柱绕流测试案例验证了其有效性。
Johns Hopkins University（约翰斯·霍普金斯大学）；Technische Universität Darmstadt（达姆施塔特工业大学）；Siemens AG（西门子股份公司）
Constructing surrogate models for uncertainty quantification (UQ) on complex partial differential equations (PDEs) having inherently high-dimensional $\mathcal{O}(10^{\ge 2})$ stochastic inputs (e.g., forcing terms, boundary conditions, initial conditions) poses tremendous challenges. The curse of dimensionality can be addressed with suitable unsupervised learning techniques used as a pre-processing tool to encode inputs onto lower-dimensional subspaces while retaining its structural information and meaningful properties. In this work, we review and investigate thirteen dimension reduction met…
K. N. Toosi University of Technology（K.N.托西工业大学）；University of Tehran（德黑兰大学）
The incremental poses computed through odometry can be integrated over time to calculate the pose of a device with respect to an initial location. The resulting global pose may be used to formulate a second, consistency based, loss term in a deep odometry setting. In such cases where multiple losses are imposed on a network, the uncertainty over each output can be derived to weigh the different loss terms in a maximum likelihood setting. However, when imposing a constraint on the integrated transformation, due to how only odometry is estimated at each iteration of the algorithm, there is no in…
Ensembling neural networks is an effective way to increase accuracy, and can often match the performance of individual larger models. This observation poses a natural question: given the choice between a deep ensemble and a single neural network with similar accuracy, is one preferable over the other? Recent work suggests that deep ensembles may offer distinct benefits beyond predictive power: namely, uncertainty quantification and robustness to dataset shift. In this work, we demonstrate limitations to these purported benefits, and show that a single (but larger) neural network can replicate …
A Comprehensive Framework for Uncertainty Quantification of Voxel-wise Supervised Models in IVIM MRI
Department of Acute Brain（急性脑和心血管损伤部门）；Department of Neuroscience（神经科学部门）；Istituto di Ricerche Farmacologiche Mario Negri IRCCS（马里奥·内格里药理研究所）；Milan（米兰）；Italy（意大利）
Uncertainty Quantification in Cardiac Model Personalisation from Ultrafast Ultrasound
Université Côte d'Azur（蔚蓝海岸大学）；Inria（法国国家信息与自动化研究所）；Bordeaux University Hospital (CHU de Bordeaux)（波尔多大学医院）；IHU Liryc, Electrophysiology and Heart Modeling Institute（Liryc大学医院研究所（电生理与心脏建模研究所））
Human Pose Estimation by Probabilistic Mixtures of Gaussian and Uniform Distributions
University of Málaga（马拉加大学）；Instituto de Investigación Biomédica de Málaga y Plataforma en Nanomedicina – IBIMA Plataforma BIONAND（马拉加生物医学与纳米医学平台研究所（IBIMA BIONAND平台））；ITIS Software（ITIS软件公司）
Provably Guaranteed Polytopic Uncertainty Quantification for SLAM
School of Data Science, The Chinese University of Hong Kong, Shenzhen（数据科学学院，香港中文大学（深圳））；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen（人工智能学院，香港中文大学（深圳））；Department of Electrical and Electronic Engineering, Imperial College London（电子与电气工程系，帝国理工学院伦敦分校）；School of Aerospace, Mechanical and Mechatronic Engineering, The University of Sydney（航空航天、机械与机电工程学院，悉尼大学）
Distributionally Robust Statistical Verification with Imprecise Neural Networks
University of British Columbia（不列颠哥伦比亚大学）；University of Manchester（曼彻斯特大学）；University of Pennsylvania（宾夕法尼亚大学）；Massachusetts Institute of Technology（麻省理工学院）；University of Florida（佛罗里达大学）；Institute for Clarity in Documentation（文档清晰研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗康校区）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）
The two-stage object pose estimation paradigm first detects semantic keypoints on the image and then estimates the 6D pose by minimizing reprojection errors. Despite performing well on standard benchmarks, existing techniques offer no provable guarantees on the quality and uncertainty of the estimation. In this paper, we inject two fundamental changes, namely conformal keypoint detection and geometric uncertainty propagation, into the two-stage paradigm and propose the first pose estimator that endows an estimation with provable and computable worst-case error bounds. On one hand, conformal ke…
Uncertainty Quantification of Set-Membership Estimation in Control and Perception: Revisiting the Minimum Enclosing Ellipsoid
Princeton University（普林斯顿大学）；LAAS-CNRS（法国国家科学研究中心LAAS实验室）；Toulouse School of Economics (TSE)（图卢兹经济学院）；School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）
Estimation of rigid transformation between two point clouds is a computationally challenging problem in vision-based relative navigation. Targeting a real-time navigation solution utilizing point-cloud and image registration algorithms, this paper develops high-performance avionics for power and resource constrained pose estimation framework. A Field-Programmable Gate Array (FPGA) based embedded architecture is developed to accelerate estimation of relative pose between the point-clouds, aided by image features that correspond to the individual point sets. At algorithmic level, the pose estima…
School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）；NVIDIA（英伟达）；ETH Zürich（苏黎世联邦理工学院）
Quantification of uncertainty in point cloud matching is critical in many tasks such as pose estimation, sensor fusion, and grasping. Iterative closest point (ICP) is a commonly used pose estimation algorithm which provides a point estimate of the transformation between two point clouds. There are many sources of uncertainty in this process that may arise due to sensor noise, ambiguous environment, and occlusion. However, for safety critical problems such as autonomous driving, a point estimate of the pose transformation is not sufficient as it does not provide information about the multiple s…
