随着稀疏TOF传感器在移动设备中的广泛应用,RGB图像引导的稀疏深度完成最近引起了广泛的关注,但仍然面临一些问题。首先,多模式信息的融合需要更多的网络模块来处理不同的模式。但是,稀疏TOF测量的应用方案通常需要轻巧的结构和低计算成本。其次,将稀疏和嘈杂的深度数据与密集像素的RGB数据融合可能会引入伪影。在本文中,提出了一个光线但有效的深度完成网络,该网络由两个分支的全球和局部深度预测模块和漏斗卷积空间传播网络组成。两分支结构的提取和融合具有轻质骨架的横模特征。改进的空间传播模块可以逐渐完善完整的深度图。此外,针对深度完成问题提出了校正后的梯度损失。实验结果表明,所提出的方法可以胜过一些具有轻量级体系结构的最先进方法。提出的方法还赢得了MIPI2022 RGB+TOF深度完成挑战的冠军。
translated by 谷歌翻译
State estimation is important for a variety of tasks, from forecasting to substituting for unmeasured states in feedback controllers. Performing real-time state estimation for PDEs using provably and rapidly converging observers, such as those based on PDE backstepping, is computationally expensive and in many cases prohibitive. We propose a framework for accelerating PDE observer computations using learning-based approaches that are much faster while maintaining accuracy. In particular, we employ the recently-developed Fourier Neural Operator (FNO) to learn the functional mapping from the initial observer state and boundary measurements to the state estimate. By employing backstepping observer gains for previously-designed observers with particular convergence rate guarantees, we provide numerical experiments that evaluate the increased computational efficiency gained with FNO. We consider the state estimation for three benchmark PDE examples motivated by applications: first, for a reaction-diffusion (parabolic) PDE whose state is estimated with an exponential rate of convergence; second, for a parabolic PDE with exact prescribed-time estimation; and, third, for a pair of coupled first-order hyperbolic PDEs that modeling traffic flow density and velocity. The ML-accelerated observers trained on simulation data sets for these PDEs achieves up to three orders of magnitude improvement in computational speed compared to classical methods. This demonstrates the attractiveness of the ML-accelerated observers for real-time state estimation and control.
translated by 谷歌翻译
Aspect Sentiment Triplet Extraction (ASTE) has become an emerging task in sentiment analysis research, aiming to extract triplets of the aspect term, its corresponding opinion term, and its associated sentiment polarity from a given sentence. Recently, many neural networks based models with different tagging schemes have been proposed, but almost all of them have their limitations: heavily relying on 1) prior assumption that each word is only associated with a single role (e.g., aspect term, or opinion term, etc. ) and 2) word-level interactions and treating each opinion/aspect as a set of independent words. Hence, they perform poorly on the complex ASTE task, such as a word associated with multiple roles or an aspect/opinion term with multiple words. Hence, we propose a novel approach, Span TAgging and Greedy infErence (STAGE), to extract sentiment triplets in span-level, where each span may consist of multiple words and play different roles simultaneously. To this end, this paper formulates the ASTE task as a multi-class span classification problem. Specifically, STAGE generates more accurate aspect sentiment triplet extractions via exploring span-level information and constraints, which consists of two components, namely, span tagging scheme and greedy inference strategy. The former tag all possible candidate spans based on a newly-defined tagging set. The latter retrieves the aspect/opinion term with the maximum length from the candidate sentiment snippet to output sentiment triplets. Furthermore, we propose a simple but effective model based on the STAGE, which outperforms the state-of-the-arts by a large margin on four widely-used datasets. Moreover, our STAGE can be easily generalized to other pair/triplet extraction tasks, which also demonstrates the superiority of the proposed scheme STAGE.
translated by 谷歌翻译
Knowledge graph technology is considered a powerful and semantically enabled solution to link entities, allowing users to derive new knowledge by reasoning data according to various types of reasoning rules. However, in building such a knowledge graph, events modeling, such as that of disasters, is often limited to single, isolated events. The linkages among cascading events are often missing in existing knowledge graphs. This paper introduces our GeoAI (Geospatial Artificial Intelligence) solutions to identify causality among events, in particular, disaster events, based on a set of spatially and temporally-enabled semantic rules. Through a use case of causal disaster events modeling, we demonstrated how these defined rules, including theme-based identification of correlated events, spatiotemporal co-occurrence constraint, and text mining of event metadata, enable the automatic extraction of causal relationships between different events. Our solution enriches the event knowledge base and allows for the exploration of linked cascading events in large knowledge graphs, therefore empowering knowledge query and discovery.
translated by 谷歌翻译
在本文中,我们研究了神经视频压缩(NVC)中位分配的问题。首先,我们揭示了最近声称是最佳的位分配方法实际上是由于其实施而是最佳的。具体而言,我们发现其亚典型性在于半损坏的变异推理(SAVI)对潜在的不正确的应用,具有非物质变异后验。然后,我们表明,在非因素潜伏期上校正的SAVI校正版本需要递归地通过梯度上升应用后传播,这是我们得出校正后的最佳位分配算法的。由于校正位分配的计算不可行性,我们设计了有效的近似值以使其实用。经验结果表明,我们提出的校正显着改善了R-D性能和比特率误差的错误分配,并且比所有其他位分配方法都大大提高了。源代码在补充材料中提供。
translated by 谷歌翻译
在本文中,我们考虑了神经视频压缩(NVC)中位分配的问题。由于帧参考结构,使用相同的R-D(速率)权衡参数$ \ lambda $的当前NVC方法是次优的,这带来了位分配的需求。与以前基于启发式和经验R-D模型的方法不同,我们建议通过基于梯度的优化解决此问题。具体而言,我们首先提出了一种基于半损坏的变异推理(SAVI)的连续位实现方法。然后,我们通过更改SAVI目标,使用迭代优化提出了一个像素级隐式分配方法。此外,我们基于NVC的可区分特征得出了精确的R-D模型。我们通过使用精确的R-D模型证明其等效性与位分配的等效性来展示我们的方法的最佳性。实验结果表明,我们的方法显着改善了NVC方法,并且胜过现有的位分配方法。我们的方法是所有可区分NVC方法的插件,并且可以直接在现有的预训练模型上采用。
translated by 谷歌翻译
从嘈杂的点云中恢复高质量的表面,称为点云降级,是几何处理中的一个基本而又具有挑战性的问题。大多数现有方法要么直接将嘈杂的输入或过滤器原始正态变为更新点位置。由点云降解和正常过滤之间的基本相互作用的动机,我们从多任务的角度重新访问点云,并提出一个名为PCDNF的端到端网络,以通过关节正常滤波来denoise点云。特别是,我们引入了一项辅助正常过滤任务,以帮助整体网络更有效地消除噪声,同时更准确地保留几何特征。除了整体体系结构外,我们的网络还具有两个新型模块。一方面,为了提高降噪性能,我们设计了一种形状感知的选择器,以全面考虑学习点,正常特征和几何学先验,以构建特定点的潜在切线空间表示。另一方面,点特征更适合描述几何细节,正常特征更有利于表示几何结构(例如,边缘和角落)。结合点和正常特征使我们能够克服它们的弱点。因此,我们设计一个功能改进模块,以融合点和正常功能,以更好地恢复几何信息。广泛的评估,比较和消融研究表明,所提出的方法在点云降解和正常过滤方面优于最先进的方法。
translated by 谷歌翻译
荧光镜检查是一种使用X射线来获得3D对象内部的实时2D视频,帮助外科医生观察病理结构和组织功能,尤其是在干预过程中。然而,它主要是由于低剂量X射线的临床使用而产生的,因此需要荧光镜检查技术。这种脱牙受到了成像对象与X射线成像系统之间的相对运动的挑战。我们通过提出一个自制的三阶段框架来应对这一挑战,从而利用荧光镜检查的领域知识。 (i)稳定:我们首先基于光流计算构建动态全景,以稳定X射线检测器的运动引起的非平稳背景。 (ii)分解:然后,我们提出了一种新型的基于掩模的鲁棒原理分析(RPCA)分解方法,以将探测器运动的视频分离为低级别背景和稀疏前景。这样的分解可容纳专家的阅读习惯。 (iii)denoise:我们终于通过自我监督的学习策略分别降低了背景和前景,并通过双侧时空滤波器将deno的部分融合到最终输出中。为了评估我们工作的有效性,我们策划了27个视频(1,568帧)和相应的地面真相的专用荧光镜数据集。我们的实验表明,与标准方法相比,它在降解和增强效果方面取得了重大改进。最后,专家评级确认了这种功效。
translated by 谷歌翻译
心血管疾病是全球死亡的主要原因,是一种与年龄有关的疾病。了解衰老期间心脏的形态和功能变化是一个关键的科学问题,其答案将有助于我们定义心血管疾病的重要危险因素并监测疾病进展。在这项工作中,我们提出了一种新型的条件生成模型,以描述衰老过程中心脏3D解剖学的变化。提出的模型是灵活的,可以将多个临床因素(例如年龄,性别)整合到生成过程中。我们在心脏解剖学的大规模横截面数据集上训练该模型,并在横截面和纵向数据集上进行评估。该模型在预测衰老心脏的纵向演化和对其数据分布进行建模方面表现出了出色的表现。
translated by 谷歌翻译
最近,未经训练的神经网络(UNNS)显示了在随机采样轨迹上对MR图像重建的令人满意的性能,而无需使用其他全面采样训练数据。但是,现有的基于UNN的方法并未完全使用MR图像物理先验,导致某些常见情况(例如部分傅立叶,常规采样等)的性能差,并且缺乏重建准确性的理论保证。为了弥合这一差距,我们使用特殊设计的UNN提出了一种保障的K空间插值方法,该方法使用特殊设计的UNN,该方法由MR图像的三个物理先验(或K空间数据)驱动,包括稀疏,线圈灵敏度平稳性和相位平滑度。我们还证明,所提出的方法保证了插值K空间数据准确性的紧密界限。最后,消融实验表明,所提出的方法比现有传统方法更准确地表征了MR图像的物理先验。此外,在一系列常用的采样轨迹下,实验还表明,所提出的方法始终优于传统的平行成像方法和现有的UNN,甚至超过了最先进的监督训练的K空间深度学习方法案例。
translated by 谷歌翻译