The advancements in the state of the art of generative Artificial Intelligence (AI) brought by diffusion models can be highly beneficial in novel contexts involving Earth observation data. After introducing this new family of generative models, this work proposes and analyses three use cases which demonstrate the potential of diffusion-based approaches for satellite image data. Namely, we tackle cloud removal and inpainting, dataset generation for change-detection tasks, and urban replanning.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
RGB-D
·
回合
·
可約的
·
Performer
·
Neural implicit representations have been explored to enhance visual SLAM algorithms, especially in providing high-fidelity dense map. Existing methods operate robustly in static scenes but struggle with the disruption caused by moving objects. In this paper we present NID-SLAM, which significantly improves the performance of neural SLAM in dynamic environments. We propose a new approach to enhance inaccurate regions in semantic masks, particularly in marginal areas. Utilizing the geometric information present in depth images, this method enables accurate removal of dynamic objects, thereby reducing the probability of camera drift. Additionally, we introduce a keyframe selection strategy for dynamic scenes, which enhances camera tracking robustness against large-scale objects and improves the efficiency of mapping. Experiments on publicly available RGB-D datasets demonstrate that our method outperforms competitive neural SLAM approaches in tracking accuracy and mapping quality in dynamic environments.
Semantic segmentation techniques for extracting building footprints from high-resolution remote sensing images have been widely used in many fields such as urban planning. However, large-scale building extraction demands higher diversity in training samples. In this paper, we construct a Global Building Semantic Segmentation (GBSS) dataset (The dataset will be released), which comprises 116.9k pairs of samples (about 742k buildings) from six continents. There are significant variations of building samples in terms of size and style, so the dataset can be a more challenging benchmark for evaluating the generalization and robustness of building semantic segmentation models. We validated through quantitative and qualitative comparisons between different datasets, and further confirmed the potential application in the field of transfer learning by conducting experiments on subsets.
Including Artificial Neural Networks in embedded systems at the edge allows applications to exploit Artificial Intelligence capabilities directly within devices operating at the network periphery. This paper introduces Spiker+, a comprehensive framework for generating efficient, low-power, and low-area customized Spiking Neural Networks (SNN) accelerators on FPGA for inference at the edge. Spiker+ presents a configurable multi-layer hardware SNN, a library of highly efficient neuron architectures, and a design framework, enabling the development of complex neural network accelerators with few lines of Python code. Spiker+ is tested on two benchmark datasets, the MNIST and the Spiking Heidelberg Digits (SHD). On the MNIST, it demonstrates competitive performance compared to state-of-the-art SNN accelerators. It outperforms them in terms of resource allocation, with a requirement of 7,612 logic cells and 18 Block RAMs (BRAMs), which makes it fit in very small FPGA, and power consumption, draining only 180mW for a complete inference on an input image. The latency is comparable to the ones observed in the state-of-the-art, with 780us/img. To the authors' knowledge, Spiker+ is the first SNN accelerator tested on the SHD. In this case, the accelerator requires 18,268 logic cells and 51 BRAM, with an overall power consumption of 430mW and a latency of 54 us for a complete inference on input data. This underscores the significance of Spiker+ in the hardware-accelerated SNN landscape, making it an excellent solution to deploy configurable and tunable SNN architectures in resource and power-constrained edge applications.
In this paper, we propose the application of shrinkage strategies to estimate coefficients in the Bell regression models when prior information about the coefficients is available. The Bell regression models are well-suited for modeling count data with multiple covariates. Furthermore, we provide a detailed explanation of the asymptotic properties of the proposed estimators, including asymptotic biases and mean squared errors. To assess the performance of the estimators, we conduct numerical studies using Monte Carlo simulations and evaluate their simulated relative efficiency. The results demonstrate that the suggested estimators outperform the unrestricted estimator when prior information is taken into account. Additionally, we present an empirical application to demonstrate the practical utility of the suggested estimators.
LiDAR is an essential sensor for autonomous driving by collecting precise geometric information regarding a scene. As the performance of various LiDAR perception tasks has improved, generalizations to new environments and sensors has emerged to test these optimized models in real-world conditions. Unfortunately, the various annotation strategies of data providers complicate the computation of cross-domain performances. This paper provides a novel dataset, ParisLuco3D, specifically designed for cross-domain evaluation to make it easier to evaluate the performance utilizing various source datasets. Alongside the dataset, online benchmarks for LiDAR semantic segmentation, LiDAR object detection, and LiDAR tracking are provided to ensure a fair comparison across methods. The ParisLuco3D dataset, evaluation scripts, and links to benchmarks can be found at the following website: //npm3d.fr/parisluco3d
This paper explores the impact of biologically plausible neuron models on the performance of Spiking Neural Networks (SNNs) for regression tasks. While SNNs are widely recognized for classification tasks, their application to Scientific Machine Learning and regression remains underexplored. We focus on the membrane component of SNNs, comparing four neuron models: Leaky Integrate-and-Fire, FitzHugh-Nagumo, Izhikevich, and Hodgkin-Huxley. We investigate their effect on SNN accuracy and efficiency for function regression tasks, by using Euler and Runge-Kutta 4th-order approximation schemes. We show how more biologically plausible neuron models improve the accuracy of SNNs while reducing the number of spikes in the system. The latter represents an energetic gain on actual neuromorphic chips since it directly reflects the amount of energy required for the computations.
In response to the transformation towards Industry 5.0, there is a growing call for manufacturing systems that prioritize environmental sustainability, alongside the emerging application of digital tools. Extended Reality (XR) - including Virtual Reality (VR), Augmented Reality (AR) and Mixed Reality (MR) - is one of the technologies identified as an enabler for Industry 5.0. XR could potentially also be a driver for more sustainable manufacturing: however, its potential environmental benefits have received limited attention. This paper aims to explore the current manufacturing applications and research within the field of XR technology connected to the environmental sustainability principle. The objectives of this paper are two-fold: (1) Identify the currently explored use cases of XR technology in literature and research, addressing environmental sustainability in manufacturing; (2) Provide guidance and references for industry and companies to use cases, toolboxes, methodologies, and workflows for implementing XR in environmental sustainable manufacturing practices. Based on the categorization of sustainability indicators, developed by the National Institute of Standards and Technology (NIST), the authors analyzed and mapped the current literature, with criteria of pragmatic XR use cases for manufacturing. The exploration resulted in a mapping of the current applications and use cases of XR technology within manufacturing that has the potential to drive environmental sustainability. The results are presented as stated use-cases with reference to the literature, contributing as guidance and inspiration for future researchers or implementations in industry, using XR as a driver for environmental sustainability. Furthermore, the authors open up the discussion for future work and research to increase the attention of XR as a driver for environmental sustainability.
Over the past decade, the value and potential of VR applications in manufacturing have gained significant attention in accordance with the rise of Industry 4.0 and beyond. Its efficacy in layout planning, virtual design reviews, and operator training has been well-established in previous studies. However, many functional requirements and interaction parameters of VR for manufacturing remain ambiguously defined. One area awaiting exploration is spatial recognition and learning, crucial for understanding navigation within the virtual manufacturing system and processing spatial data. This is particularly vital in multi-user VR applications where participants' spatial awareness in the virtual realm significantly influences the efficiency of meetings and design reviews. This paper investigates the interaction parameters of multi-user VR, focusing on interactive positioning maps for virtual factory layout planning and exploring the user interaction design of digital maps as navigation aid. A literature study was conducted in order to establish frequently used technics and interactive maps from the VR gaming industry. Multiple demonstrators of different interactive maps provide a comprehensive A/B test which were implemented into a VR multi-user platform using the Unity game engine. Five different prototypes of interactive maps were tested, evaluated and graded by the 20 participants and 40 validated data streams collected. The most efficient interaction design of interactive maps is thus analyzed and discussed in the study.
Convergence of classical parallel iterations is detected by performing a reduction operation at each iteration in order to compute a residual error relative to a potential solution vector. To efficiently run asynchronous iterations, blocking communication requests are avoided, which makes it hard to isolate and handle any global vector. While some termination protocols were proposed for asynchronous iterations, only very few of them are based on global residual computation and guarantee effective convergence. But the most effective and efficient existing solutions feature two reduction operations, which constitutes an important factor of termination delay. In this paper, we present new, non-intrusive, protocols to compute a residual error under asynchronous iterations, requiring only one reduction operation. Various communication models show that some heuristics can even be introduced and formally evaluated. Extensive experiments with up to 5600 processor cores confirm the practical effectiveness and efficiency of our approach.
Terrain surface roughness, often described abstractly, poses challenges in quantitative characterisation with various descriptors found in the literature. This study compares five commonly used roughness descriptors, exploring correlations among their quantified terrain surface roughness maps across three terrains with distinct spatial variations. Additionally, the study investigates the impacts of spatial scales and interpolation methods on these correlations. Dense point cloud data obtained through Light Detection and Ranging technique are used in this study. The findings highlight both global pattern similarities and local pattern distinctions in the derived roughness maps, emphasizing the significance of incorporating multiple descriptors in studies where local roughness values play a crucial role in subsequent analyses. The spatial scales were found to have a smaller impact on rougher terrain, while interpolation methods had minimal influence on roughness maps derived from different descriptors.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191