Applied Intelligence最新文献_第3页

Dual attention-guided distillation for class incremental semantic segmentation

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-04-01 DOI: 10.1007/s10489-025-06436-y

Pengju Xu, Yan Wang, Bingye Wang, Haiying Zhao

{"title":"Dual attention-guided distillation for class incremental semantic segmentation","authors":"Pengju Xu, Yan Wang, Bingye Wang, Haiying Zhao","doi":"10.1007/s10489-025-06436-y","DOIUrl":"10.1007/s10489-025-06436-y","url":null,"abstract":"<div><p>Class Incremental Semantic Segmentation (CISS) aims at segmenting the incremental new classes without losing the ability on old classes. Currently, some CISS methods based on feature knowledge distillation suffer from the stability-plasticity dilemma, <i>i.e.</i>, excessive knowledge distillation may impede models from learning new classes. Besides, distilling without emphasis fails to preserve old knowledge effectively. To address these issues, a more fine-grained and focused approach to knowledge transfer, named dual attention-guided distillation (DAGD), is proposed for the CISS task. This approach not only ensures that the inherited knowledge is distilled in a targeted manner but also allows the model to adapt and learn new knowledge more efficiently. DAGD model contains a channel attention-guided distillation module and a spatial attention-guided distillation module. The former distills channel-wise attention maps to improve the knowledge transfer of essential channels while accommodating new knowledge learning. The latter encodes a weight coefficient map to highlight important regions in the spatial dimension, which further decouples old knowledge retention and new knowledge entry. Furthermore, a dynamic temperature strategy is introduced to facilitate logit knowledge distillation, specifically sharpening the predictive distribution produced by the output of the old model, thus achieving more accurate knowledge transfer. Extensive experimental results on Pascal VOC 2012 and ADE20K datasets demonstrate that our method achieves competitive results.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive patch selection to improve Vision Transformers through Reinforcement Learning

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-04-01 DOI: 10.1007/s10489-025-06516-z

Francesco Cauteruccio, Michele Marchetti, Davide Traini, Domenico Ursino, Luca Virgili

{"title":"Adaptive patch selection to improve Vision Transformers through Reinforcement Learning","authors":"Francesco Cauteruccio, Michele Marchetti, Davide Traini, Domenico Ursino, Luca Virgili","doi":"10.1007/s10489-025-06516-z","DOIUrl":"10.1007/s10489-025-06516-z","url":null,"abstract":"<div><p>In recent years, Transformers have revolutionized the management of Natural Language Processing tasks, and Vision Transformers (ViTs) promise to do the same for Computer Vision ones. However, the adoption of ViTs is hampered by their computational cost. Indeed, given an image divided into patches, it is necessary to compute for each layer the attention of each patch with respect to all the others. Researchers have proposed many solutions to reduce the computational cost of attention layers by adopting techniques such as quantization, knowledge distillation and manipulation of input images. In this paper, we aim to contribute to the solution of this problem. In particular, we propose a new framework, called AgentViT, which uses Reinforcement Learning to train an agent that selects the most important patches to improve the learning of a ViT. The goal of AgentViT is to reduce the number of patches processed by a ViT, and thus its computational load, while still maintaining competitive performance. We tested AgentViT on CIFAR10, FashionMNIST, and Imagenette<span>(^+)</span> (which is a subset of ImageNet) in the image classification task and obtained promising performance when compared to baseline ViTs and other related approaches available in the literature.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-025-06516-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Advanced IDS: a comparative study of datasets and machine learning algorithms for network flow-based intrusion detection systems

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-04-01 DOI: 10.1007/s10489-025-06422-4

Jose Carlos Mondragon, Paula Branco, Guy-Vincent Jourdan, Andres Eduardo Gutierrez-Rodriguez, Rajesh Roshan Biswal

{"title":"Advanced IDS: a comparative study of datasets and machine learning algorithms for network flow-based intrusion detection systems","authors":"Jose Carlos Mondragon, Paula Branco, Guy-Vincent Jourdan, Andres Eduardo Gutierrez-Rodriguez, Rajesh Roshan Biswal","doi":"10.1007/s10489-025-06422-4","DOIUrl":"10.1007/s10489-025-06422-4","url":null,"abstract":"<div><p>Globally, cyberattacks are growing and mutating each month. Intelligent Intrusion Network Detection Systems are developed to analyze and detect anomalous traffic to face these threats. A way to address this is by using network flows, an aggregated version of communications between devices. Network Flow datasets are used to train Artificial Intelligence (AI) models to classify specific attacks. Training these models requires threat samples usually generated synthetically in labs as capturing them on operational network is a challenging task. As threats are fast-evolving, new network flows are continuously developed and shared. However, using old datasets is still a popular procedure when testing models, hindering a more comprehensive characterization of the advantages and opportunities of recent solutions on new attacks. Moreover, a standardized benchmark is missing rendering a poor comparison between the models produced by algorithms. To address these gaps, we present a benchmark with fourteen recent and preprocessed datasets and study seven categories of algorithms for Network Intrusion Detection based on Network Flows. We provide a centralized source of pre-processed datasets to researchers for easy download. All dataset are also provided with a train, validation and test split to allow a straightforward and fair comparison between existing and new solutions. We selected open state-of-the-art publicly available algorithms, representatives of diverse approaches. We carried out an experimental comparison using the Macro F1 score of these algorithms. Our results highlight each model operation on dataset scenarios and provide guidance on competitive solutions. Finally, we discuss the main characteristics of the models and benchmarks, focusing on practical implications and recommendations for practitioners and researchers.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-025-06422-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DAGAF: A directed acyclic generative adversarial framework for joint structure learning and tabular data synthesis

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-31 DOI: 10.1007/s10489-025-06410-8

Hristo Petkov, Calum MacLellan, Feng Dong

{"title":"DAGAF: A directed acyclic generative adversarial framework for joint structure learning and tabular data synthesis","authors":"Hristo Petkov, Calum MacLellan, Feng Dong","doi":"10.1007/s10489-025-06410-8","DOIUrl":"10.1007/s10489-025-06410-8","url":null,"abstract":"<div><p>Understanding the causal relationships between data variables can provide crucial insights into the construction of tabular datasets. Most existing causality learning methods typically focus on applying a single identifiable causal model, such as the Additive Noise Model (ANM) or the Linear non-Gaussian Acyclic Model (LiNGAM), to discover the dependencies exhibited in observational data. We improve on this approach by introducing a novel dual-step framework capable of performing both causal structure learning and tabular data synthesis under multiple causal model assumptions. Our approach uses Directed Acyclic Graphs (DAG) to represent causal relationships among data variables. By applying various functional causal models including ANM, LiNGAM and the Post-Nonlinear model (PNL), we implicitly learn the contents of DAG to simulate the generative process of observational data, effectively replicating the real data distribution. This is supported by a theoretical analysis to explain the multiple loss terms comprising the objective function of the framework. Experimental results demonstrate that DAGAF outperforms many existing methods in structure learning, achieving significantly lower Structural Hamming Distance (SHD) scores across both real-world and benchmark datasets (Sachs: 47%, Child: 11%, Hailfinder: 5%, Pathfinder: 7% improvement compared to state-of-the-art), while being able to produce diverse, high-quality samples.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-025-06410-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SentimentMapper: A framework for mapping of sentiments towards disaster response using social media data

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-31 DOI: 10.1007/s10489-025-06442-0

Tanu Gupta, Aman Rai, Sudip Roy

{"title":"SentimentMapper: A framework for mapping of sentiments towards disaster response using social media data","authors":"Tanu Gupta, Aman Rai, Sudip Roy","doi":"10.1007/s10489-025-06442-0","DOIUrl":"10.1007/s10489-025-06442-0","url":null,"abstract":"<div><p>Social networking platforms have been generating a massive amount of data in real-time that can be analysed and used to support government and relief organizations in preparing quick and effective action plans for disaster response. Effective disaster response requires a broad understanding of disaster situations, such as the emergency necessities of the people, their sentiments towards emergency needs, and the geographical distribution of their requirements and opinions. However, in literature, many studies exist that estimate the emotions and sentiments of the people during a disaster; they are inept in identifying and mapping the public sentiments toward emergency needs. This paper proposes a framework called <i>SentimentMapper</i>. This framework quickly maps the sentiments of people toward emergency needs using social media data to plan for effective disaster response. In order to perform an automatic analysis of sentiments using Twitter (re-branded to X since July 2023) data, we introduce a BERT Convolutional Neural Network (BCNN). BCNN performs the sentiment analysis of the collected data from the disaster-affected people regarding essential needs like food, shelter, medical emergency, and rescue during different disasters. Next, we present a tweet-text independent approach to detect the location of the tweets posted on Twitter and discover the impacts in different areas due to any disaster event. Furthermore, we also study the variations in public attitudes about the essential needs during identical or different disasters. As a case study, the proposed framework has been used on the dataset collected from Twitter during the Assam flood 2021 in India and validated with the corresponding survey reports published by the government agency. The detailed results of the analytics in the proposed framework and its validation with the case study data confirm that it is capable of providing credible situational information quickly required for the disaster responses.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards accurate post-training quantization for reparameterized models

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-31 DOI: 10.1007/s10489-025-06418-0

Luoming Zhang, Yefei He, Wen Fei, Zhenyu Lou, Weijia Wu, Yangwei Ying, Hong Zhou

{"title":"Towards accurate post-training quantization for reparameterized models","authors":"Luoming Zhang, Yefei He, Wen Fei, Zhenyu Lou, Weijia Wu, Yangwei Ying, Hong Zhou","doi":"10.1007/s10489-025-06418-0","DOIUrl":"10.1007/s10489-025-06418-0","url":null,"abstract":"<div><p>Model reparameterization is a widely accepted technique for improving inference speed without compromising performance. However, current Post-training Quantization (PTQ) methods often lead to significant accuracy degradation when applied to reparameterized models. This is primarily caused by channel-specific and sample-specific outliers, which appear only at specific samples and channels and impact on the selection of quantization parameters. To address this issue, we propose RepAPQ, a novel framework that preserves the accuracy of quantized reparameterization models. Different from previous frameworks using Mean Squared Error (MSE) as a measurement, we utilize Mean Absolute Error (MAE) to mitigate the influence of outliers on quantization parameters. Our framework consists of two core components: Quantization Protecting Reparameterization and Across-block Calibration. For effective calibration, Quantization Protecting Reparameterization combines multiple branches into a single convolution with an affine layer. During training, the affine layer accelerates convergence and amplifies the output of the convolution to better accommodate samples with outliers. Additionally, Across-block Calibration leverages the measurement of stage output as supervision to address the gradient problem introduced by MAE and enhance the interlayer correlation with quantization parameters. Comprehensive experiments demonstrate the effectiveness of RepAPQ across various models and tasks. Our framework outperforms previous methods by approximately 1% for 8-bit PTQ and 2% for 6-bit PTQ, showcasing its superior performance. The code is available at https://github.com/ilur98/DLMC-QUANT.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Leveraging BiLSTM-GAT for enhanced stock market prediction: a dual-graph approach to portfolio optimization

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-31 DOI: 10.1007/s10489-025-06462-w

Xiaobin Lu, Josiah Poon, Matloob Khushi

{"title":"Leveraging BiLSTM-GAT for enhanced stock market prediction: a dual-graph approach to portfolio optimization","authors":"Xiaobin Lu, Josiah Poon, Matloob Khushi","doi":"10.1007/s10489-025-06462-w","DOIUrl":"10.1007/s10489-025-06462-w","url":null,"abstract":"<div><p>Stock price prediction remains a critical challenge in financial research due to its potential to inform strategic decision-making. Existing approaches predominantly focus on two key tasks: (1) regression, which forecasts future stock prices, and (2) classification, which identifies trading signals such as buy, sell, or hold. However, the inherent limitations of financial data hinder effective model training, often leading to suboptimal performance. To mitigate this issue, prior studies have expanded datasets by aggregating historical data from multiple companies. This strategy, however, fails to account for the unique characteristics and interdependencies among individual stocks, thereby reducing predictive accuracy. To address these limitations, we propose a novel BiLSTM-GAT-AM model that integrates bidirectional long short-term memory (BiLSTM) networks with graph attention networks (GAT) and an attention mechanism (AM). Unlike conventional graph-based models that define edges based solely on technical or fundamental relationships, our approach employs a dual-graph structure: one graph captures technical similarities, while the other encodes fundamental industry relationships. These two representations are aligned through an attention mechanism, enabling the model to exploit both technical and fundamental insights for enhanced stock market predictions. We conduct extensive experiments, including ablation studies and comparative evaluations against baseline models. The results demonstrate that our model achieves superior predictive performance. Furthermore, leveraging the model’s forecasts, we construct an optimized portfolio and conduct backtesting on the test dataset. Empirical results indicate that our portfolio consistently outperforms both baseline models and the S&P 500 index, highlighting the effectiveness of our approach in stock market prediction and portfolio optimization.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-025-06462-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel three-way heterogeneous multi-attribute group decision method based on LINMAP for college teacher introduction

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-31 DOI: 10.1007/s10489-025-06369-6

Shu-Ping Wan, Yu Gao, Jiu-Ying Dong

{"title":"A novel three-way heterogeneous multi-attribute group decision method based on LINMAP for college teacher introduction","authors":"Shu-Ping Wan, Yu Gao, Jiu-Ying Dong","doi":"10.1007/s10489-025-06369-6","DOIUrl":"10.1007/s10489-025-06369-6","url":null,"abstract":"<div><p>With dramatic development of Chinese social economics and higher education, college teacher introduction has become an urgent and important problem, which is a type of heterogeneous multi-attribute group decision-making (HMAGDM). This article erects a novel three-way decision (TWD) model based on LINMAP (Linear Programming Technique for Multidimensional Analysis of Preference) to handle HMAGDM and applies to college teacher introduction. Firstly, combining evaluation matrices with alternatives’ preferences offered by decision makers (DMs), we define the individual consistency and inconsistency indexes, group consistency and inconsistency indexes. In terms of the individual consistency and inconsistency indexes, the weights of DMs are determined through establishing a bi-objective mathematical optimization model. As per the group consistency and inconsistency indexes, we build a bi-objective optimization model to derive the attribute weights and the fuzzy ideal solutions (FISs) which are employed to calculate the relative profit functions. Using the DMs’ weights, we could obtain the collective overall profit functions of alternatives and the thresholds. The conditional probability of each alternative is acquired according to the relative closeness coefficient. The classification rules and decision results are further induced based on maximum-profit decision principle. An example of college teacher introduction is illustrated to verify the efficacy of the erected method.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740828","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generality-aware self-supervised transformer for multivariate time series anomaly detection

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-31 DOI: 10.1007/s10489-025-06481-7

Yucheol Cho, Jae-Hyeok Lee, Gyeongdo Ham, Donggon Jang, Dae-shik Kim

{"title":"Generality-aware self-supervised transformer for multivariate time series anomaly detection","authors":"Yucheol Cho, Jae-Hyeok Lee, Gyeongdo Ham, Donggon Jang, Dae-shik Kim","doi":"10.1007/s10489-025-06481-7","DOIUrl":"10.1007/s10489-025-06481-7","url":null,"abstract":"<div><p>Efficient identification of anomalies within multivariate time series data holds significant relevance in contemporary industrial settings. The challenge lies in swiftly and accurately pinpointing anomalous data points. This challenge is further compounded by factors such as the absence of labeled anomalies, data volatility, and the need for ultra-fast inference times. While previous approaches have introduced advanced deep learning models to address these challenges, comprehensive efforts to tackle all these issues simultaneously have been limited. Recent developments in unsupervised learning-based models have demonstrated remarkable performance. However, many of these models rely on reconstruction error as an anomaly score, making them sensitive to unseen normal data patterns. To address this limitation, we propose a novel framework, generality-aware self-supervised transformer for multivariate time series anomaly detection, which utilizes a transformer that effectively generalizes normal data patterns through self-knowledge distillation. Furthermore, we incorporate an auxiliary decoder to compute generality-based anomaly scores, thereby enhancing the differentiation between anomalous and normal data points in testing datasets. In our study, encompassing a diverse range of publicly available datasets and our own extracted data from linear motion (LM) guides and reducers built to model the vertical and rotational motions of robots, we establish the superior anomaly detection performance of our framework compared to existing state-of-the-art models. Notably, we verify that this improved performance is achieved while also considering time efficiency.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Structured 3D gaussian splatting for novel view synthesis based on single RGB-LiDAR View

IF 3.4 2区计算机科学

Applied Intelligence Pub Date : 2025-03-31 DOI: 10.1007/s10489-025-06494-2

Libin Liu, Zhiqun Zhao, Wei Ma, Siyuan Zhang, Hongbin Zha

{"title":"Structured 3D gaussian splatting for novel view synthesis based on single RGB-LiDAR View","authors":"Libin Liu, Zhiqun Zhao, Wei Ma, Siyuan Zhang, Hongbin Zha","doi":"10.1007/s10489-025-06494-2","DOIUrl":"10.1007/s10489-025-06494-2","url":null,"abstract":"<div><p>3D scene reconstruction is a critical task in computer vision and graphics, with recent advancements in 3D Gaussian Splatting (3DGS) demonstrating impressive novel view synthesis (NVS) result. However, most 3DGS methods rely on multi-view images, which are not always available, particularly in outdoor environments. In this paper, we explore 3D scene reconstruction using only single-view data, comprising an RGB image and sparse point clouds from a LiDAR sensor. To address the challenges posed by limited reference and LiDAR sensor insufficient point clouds, we propose a voxel-based structured 3DGS framework enhanced with depth prediction. We introduce a novel depth prior guided voxel growing and pruning algorithm, which leverages predicted depth maps to refine scene structure and improve rendering quality. Furthermore, we design a virtual background fitting method with an adaptive voxel size to accommodate the sparse distribution of LiDAR data in outdoor scenes. Our approach surpasses existing methods, including Scaffold-GS, Gaussian-Pro, 3DGS, Mip-splatting and UniDepth, in terms of PSNR, SSIM, LPIPS and FID metrics on the KITTI and Waymo datasets, demonstrating its effectiveness in single-viewpoint 3D reconstruction and NVS.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0