This review explores the evolution from IoT to the Internet of Everything (IoX) within the cyber-physical-social-thinking (CPST) hyperspace, centering on the emerging challenge of ”relationship explosion.” As interconnected systems grow in scale and complexity, the exponential proliferation of internal (e.g., device coordination, data aggregation) and cross-space (e.g., streaming, translating, adapting) relationships leading to scalability, security, and real-time processing challenges. Through a systematic literature review guided by five research questions, we analyze how this relational explosion intensifies across IoX domains—spanning IoT, IoP, and IoTk—and undermines the efficacy of Artificial Narrow Intelligence (ANI) in managing dynamic, heterogeneous environments. This review proposes that Artificial General Intelligence (AGI) offers a transformative solution, enabling adaptive reasoning, cognitive firewalls, and unified decision-making to navigate complex relationship networks. AGI-driven methodologies enhance system resilience, security, and efficiency in aggregating, moderating, and evolving relationships across CPST spaces. The paper outlines a classification of relationship types, evaluates AGI’s advantages over ANI, and proposes a future research roadmap emphasizing ethical governance, human-AGI collaboration, and sustainable architectures. By framing IoX development around the management of relationship explosion, we provide a roadmap for future research, emphasizing interdisciplinary efforts, ethical governance, and sustainable frameworks to foster intelligent, socially aware IoX ecosystems.

Interactive segmentation (IS) using minimal prompts like points and bounding boxes facilitates rapid image annotation, which is crucial for enhancing data-driven deep learning methods. Traditional IS methods, however, process only one target per interaction, leading to inefficiency when annotating multiple identical-class objects in remote sensing imagery (RSI). To address this issue, we present a new task—identical-class object detection (ICOD) for rapid IS in RSI. This task aims to only identify and detect all identical-class targets within an image, guided by a specific category target in the image with its mask. For this task, we propose an ICOD network (ICODet) with a two-stage object detection framework, which consists of a backbone, feature similarity analysis module (S3QFM), and an identical-class object detector. In particular, the S3QFM analyzes feature similarities from images and support objects at both feature-space and semantic levels, generating similarity maps. These maps are processed by a region proposal network (RPN) to extract target-level features, which are then refined through a simple feature comparison module and classified to precisely identify identical-class targets. To evaluate the effectiveness of this method, we construct two datasets for the ICOD task: one containing a diverse set of buildings and another containing multicategory RSI objects. Experimental results show that our method outperforms the compared methods on both datasets. This research introduces a new method for rapid IS of RSI and advances the development of fast interaction modes, offering significant practical value for data production and fundamental applications in the remote sensing community.

In this research, we introduce the enhanced automated quality assessment network (IBS-AQSNet), an innovative solution for assessing the quality of interactive building segmentation within high-resolution remote sensing imagery. This is a new challenge in segmentation quality assessment, and our proposed IBS-AQSNet allievate this by identifying missed and mistaken segment areas. First of all, to acquire robust image features, our method combines a robust, pre-trained backbone with a lightweight counterpart for comprehensive feature extraction from imagery and segmentation results. These features are subsequently fused using simple convolution layers with residual connections. Additionally, IBS-AQSNet incorporates a multi-scale differential quality assessment decoder, proficient in pinpointing areas where segmentation result is either missed or mistaken. Experiments on a newly-built EVLab-BGZ dataset, which includes over 39,198 buildings, demonstrate the superiority of the proposed method in automating segmentation quality assessment, thereby setting a new benchmark in the field.

Spectrum is the fundamental medium for transmitting information services, including communication, navigation, and detection. Spectrum anomalies can lead to substantial economic losses and even endanger life safety. Anomaly detection constitutes a critical component of spectrum risk management. Through spectrum anomaly detection (SAD), anomalous spectrum usage behaviors, such as malicious user activities, can be identified. Given the significant limitations of current SAD algorithms in terms of accuracy and localization capabilities, this article proposes an approach for detecting spectral anomalies that utilizes knowledge distillation and memory-enhanced autoencoders (AEs). First, the pretrained network with robust feature extraction capabilities is distilled into the teacher network. Subsequently, both an AE and a memory-enhanced AE with an identical structure are trained to predict the teacher network’s normalized outputs on a spectrum devoid of anomalies. Finally, in the case of an anomalous spectrum, difference exist between the normalized outputs of the teacher network and the outputs of different student networks, as well as among the outputs of different student networks, which facilitates the process of anomaly detection. The outcomes of experiments reveal that the proposed algorithm is more effective on both synthetic spectral data sets and real IQ signals, demonstrating its proficiency in accurately detecting and locating anomalies.

Semantic segmentation of airborne laser scanning (ALS) point clouds is a valuable yet challenging task in remote sensing. When processing large-scale ALS scenes, it is necessary to partition them into smaller blocks for ease of handling. However, this partitioning introduces a challenge in capturing the ample spatial context within each block to adequately recognize the objects with a significant spatial span. This limitation becomes particularly pronounced when relying solely on the 3D representations as the input of nerual networks. To incorporate sufficient contextual information in ALS data semantic segmentation, we propose a multi-modal-based segmentation framework called projection-based context embedding (PCE) in this study. PCE effectively combines the advantages of 2D image and 3D point-voxel representations, which are the computational efficiency and the representation capability for fine-grained 3D geometries. The 2D projection is used to encode a large-scale semantic context, which is computationally expensive to be obtained using only pure 3D representation. Simultaneously, the sparse-point-voxel convolution (SPVConv) is employed to focus on learning 3D features from a small block of points centered on the large-scale context. Finally, to fully exploit the power of each modality, the embedding disentangling (ED) strategy is proposed additionally to combine the context embedding from the 2D image with 3D features for the final prediction. We demonstrate the state-of-the-art performance of PCE through extensive experiments on public large-scale ALS point cloud datasets.

Recent learning-based models excel in point cloud registration for low-overlap scenes but falter in scenarios with minimal overlap. In this article, we propose a novel method to address the extreme case of low-overlap registration: non-overlapping point cloud registration. This scenario involves input point clouds that do not have overlapping regions but are adjacent to each other after registration. While the practical application value of non-overlapping point cloud registration remains to be explored, we believe that researching this issue contributes to enhancing the performance of registration in scenarios with extremely low overlap. Abandoning conventional overlapping region detection, we directly generate the registered source point cloud with SCREAM, a generative adversarial network (GAN). The generator incorporates information from the target point cloud into the source point cloud’s features and generates the registered source point cloud. To further align the generated results with the target point cloud, we propose a differentiable renderer that renders both the target and predicted point clouds into depth maps. These depth maps are then used as inputs to a discriminator to determine whether the generated results align with the target point cloud. Rigid transformation can be directly estimated from the correspondences between the source and the generated point clouds, bypassing the need for detecting overlapping regions, feature matching, and RANSAC steps found in previous methods. Extensive experiments demonstrate that SCREAM not only outperforms common overlapping point cloud registration scenarios but also achieves a registration success rate of 52.6% for the first time in non-overlapping scenes. We also constructed a new indoor scene registration dataset, 3DZeroMatch, specifically designed to explore non-overlapping registration problems. Our code and the dataset 3DZeroMatch are accessible athttps://github.com/xujiabo/SCREAM/.

Point cloud completion aims to predict the missing part for an incomplete 3D shape. Existing point cloud completion methods based on deep learning complete the point cloud by extracting global features from the incomplete point cloud. However, such methods cannot generate a uniformly distributed point cloud and the accurate structure details of the object. To solve the problem, a novel method for completing point clouds is proposed in this paper. Our approach is a two-step strategy. First, to predict the sparse point cloud with uniform density, the Sequence Generation Completion (SGC) method is proposed. By numbering the subspace obtained from the spatial subdivision, the point cloud is represented with a sequence of numbers and the point cloud completion problem is turned into a sequence generation problem. Second, to obtain the dense point cloud and generate the accurate structural details of point clouds, we propose a resolution scale network (RSN). This network takes local resolution as input and increases the weight of low-resolution regions by learning to preserve the comprehensive structural information of the sparse point cloud, which is crucial to generate dense point cloud. The comprehensive experiments on several public datasets demonstrate the effectiveness of our method. Source code and pretrained models will be available at github.com/Pikachu-NCU/Sequence-Generate-Completion-Method.

Existing point cloud registration models suffer from large performance loss in low overlap scenarios, while the generalization ability of most models are weak. In this paper, we design a new model for point cloud registration pursing better low-overlap performance and generalization ability. On the one hand, to solve the registration problem in low-overlap scenes, we propose a novel full convolutional network searching for super points located in the overlapping region and generating feature descriptors at the super points simultaneously. The new network aims at extracting points beyond non-overlapping or smooth regions. On the other hand, we introduce a rotation-invariant convolution strategy for the fully convolutional model so that the extracted feature descriptors have rotation invariance, which improves the generalization performance of the features. Our method is tested on 3DMatch, 3DLoMatch, KITTI, and ETH, and compared with state-of-the-art methods. The experimental results demonstrate that our method can achieve the best performance in low-overlap registration tasks, and it performs well across unseen scenarios with different sensor modalities.

Point cloud completion aims to infer the complete point clouds from incomplete ones, which is used in remote sensing applications such as reconstructing and autonomous driving. However, most existing methods cannot recover accurate structure details of the object. In this paper, we propose point shift network (PS-Net). Our main contributions lie in the following three-folds. First, we propose a multi-resolution encoder, which extracts and fuses multi-resolution point cloud features hierarchically, thus avoiding information loss caused by a single global feature. Second, we design a multi-resolution point cloud generation structure, which can be combined with the multi-resolution encoder to generate gradually dense point clouds, avoiding the problem of non-uniformly density of the single-layer decoder. Third, we design the shift network, which is used to generate shift vectors to shift the coordinates of each point cloud, so as to further finetune the coordinate positions of point clouds, achieving more accurate prediction. We conduct comprehensive experiments on ShapeNet, KITTI, ScanObjectNN, and ModelNet40 datasets, which demonstrate that the proposed PS-Net achieves better performance than existing methods and verify the robustness of the proposed method. This paper contributes a new method to point cloud completion, realizes fine point cloud shape completion, and brings new possibilities to the research of autonomous driving, registration, and reconstruction.

ZigBee is one of the communication protocols used in the Internet of Things (IoT) applications. In typical deployment scenarios involving low-cost and low-power IoT devices, many communication features are disabled, consequently affecting the security offered by ZigBee. The ZigBee specification assumes that deployment of frame counters is sufficient to mitigate replay attacks in secure ZigBee networks. However, we demonstrate that it is insufficient in this paper (i.e., the network is no longer secure after the coordinator restarts). As a countermeasure, we present a timestamp-based scheme to mitigate replay attacks. Our mitigation strategy does not consume power significantly, and fully powered devices will be responsible for providing power-constrained devices with the current timestamp. The proposed scheme is designed for all ZigBee topologies and different states of ZigBee End Devices (ZEDs). Findings from our evaluation show that the proposed scheme can successfully mitigate replay attacks, with no significant network performance degradation even assuming a worst-case scenario (i.e., many devices are sending data simultaneously).