RadioVIL is proposed, an efficient two-stage framework that reformulates joint radio map inpainting and zero-shot vehicle localization as a prior-guided physical inverse problem and unlocks accurate zero-shot vehicle localization directly from sparse radio maps, paving a robust way for ISAC at the 6G edge.
Abstract
High-precision radio map construction is essential for emerging 6G Integrated Sensing and Communication (ISAC) applications, including digital twins and intelligent transportation. However, existing deep learning methods predominantly treat this as a pure image completion task, resulting in over-smoothed reconstructions that fundamentally erase high-frequency scattering signatures of dynamic physical entities such as hidden vehicles. To overcome this, we propose RadioVIL, an efficient two-stage framework that reformulates joint radio map inpainting and zero-shot vehicle localization as a prior-guided physical inverse problem. Specifically, we first train a Denoising Diffusion Probabilistic Model (DDPM) to capture the structural generative prior of the environment. During inference from highly sparse measurements, we employ a Diffusion-based Mediating Intermediate Layer Optimization (DMILO) algorithm. By optimizing an L1-regularized sparse deviation term, DMILO mathematically isolates vehicle scattering anomalies layer-by-layer without unfolding the entire denoising chain. Extensive experiments demonstrate that while conventional reconstruction baselines fail to detect hidden vehicles, and the zero-shot diffusion baseline achieves only limited detection ability due to forced semantic harmonization, RadioVIL preserves authentic physical textures, yielding the best LPIPS of 0.0587 in our evaluation. Uniquely, it unlocks accurate zero-shot vehicle localization directly from sparse radio maps, securing a 75.20% Recall and a 3.31-meter average error, paving a robust way for ISAC at the 6G edge.
Reliable dynamic spectrum access in wide-area cognitive radio networks (CRNs) is challenged by sparse and erroneous spectrum-sensing measurements. This work formulates spatial-spectrum occupancy reconstruction as an image inpainting problem and proposes two cascaded deep learning models: a bidirectional long short-term memory-based image inpainting model (BiLSTM-IIM) and a binary diffusion-based image inpainting model (Diff-IIM). In both models, Stage 1 corrects sensing errors at observed locations, while Stage 2 reconstructs missing entries. The models are evaluated using simulations of a 2500m×2500m cognitive radio network with 50–200 secondary users, five primary users, and three spatial resolutions under representative wireless conditions. Both models generally outperform total variation and matrix completion baselines under sparse and noisy observations. Under moderate sensing errors, BiLSTM-IIM achieves accuracies of 92.91%, 93.66%, and 91.17% at the 10×10, 20×20, and 30×30 resolutions, respectively, while Diff-IIM achieves lower false-alarm rates with fewer parameters. Stage 1 reduces the sensing-error rate by approximately 58% for BiLSTM-IIM and 61% for Diff-IIM. These results support deep learning-based inpainting for wide-area spectrum occupancy reconstruction under the evaluated conditions.
Taoreed A. Akinola, Xiangfang Li, Li-Jun Qian· Telecom· 0 citations
Hyperspectral image change detection (CD) has garnered significant attention in the field of remote sensing. A critical task within CD is anomaly CD. Current generative anomaly CD methods, such as diffusion models, typically rely on computationally expensive iterative sampling to extract features, severely limiting their real-time application capabilities. Furthermore, in the absence of labeled data, existing unsupervised algorithms struggle to effectively distinguish subtle target variations from background artifacts caused by shadows or registration errors. To address these challenges, we propose a novel hyperspectral anomaly CD method named efficient latent denoising-inspired network (ELDI-Net). It employs a one-step manifold projection paradigm, achieving high computational efficiency while preserving the noise-robustness advantages of generative models. Specifically, we introduce a one-step latent manifold projection framework that transforms traditional iterative denoising into a deterministic latent mapping via an encoder–projector–decoder architecture, achieving a substantial improvement in inference speed. In addition, a spectral adaptive calibration projection module is constructed, employing channel-adaptive calibration to suppress spectral redundancy while effectively preserving critical features of subtle targets. A bidirectional focus alignment mechanism is designed for implicit semantic denoising under self-supervised conditions, suppressing pseudovariation artifacts through twin cross-prediction. Finally, a GCI strategy is introduced to eliminate directional sensor noise. Experimental results on three datasets demonstrate that the proposed ELDI-Net method achieves superior or highly competitive performance compared to multiple state-of-the-art approaches.
Xing Hu, Xiang-Cheng Liu, Chen-Xi Guo et al.· IEEE Journal of Selected Top...· 0 citations
Remote sensing images are frequently degraded by occlusions and missing observations, which significantly affect subsequent interpretation and analysis. Matrix completion provides an effective solution for recovering incomplete data; however, existing deep learning-based approaches often rely on random initialization, resulting in slow optimization and limited reconstruction quality under severe missing conditions. To address these issues, this paper proposes a two-stage neural network-based matrix completion framework that combines SVD-guided low-rank modeling with convolutional feature learning. Specifically, truncated singular value decomposition (SVD) is first employed to initialize the network and provide a coarse reconstruction by jointly modeling the global low-rank structure and nonlinear image representations. A U-Net-based convolutional autoencoder is then used to refine the reconstruction by exploiting local spatial correlations and multi-scale features. In addition, a channel aggregation strategy is introduced to improve structural consistency for multi-channel remote sensing images. The proposed framework adopts a training-data-free optimization paradigm, eliminating the need for external training datasets by optimizing the network parameters directly for each input image. Experimental results on synthetic and real remote sensing images demonstrate that the proposed method consistently outperforms conventional matrix completion methods and achieves competitive performance compared with recent deep learning approaches, particularly under random missing patterns and high missing-rate scenarios.
Jie He, Zijian Lin, Tianyao Huang et al.· Remote Sensing· 0 citations
A dehazing framework named DKS-Net is proposed which fully utilizes the physics guiding features and extracting structural information in the spatial domain, and a Kernel Selective Feature Extraction Module (KSFE) is introduced to effectively captures structural patterns via large-kernel convolutions with dynamic selection capabilities and multi-scale semantic cues.
Zehao Shi, Han Wang, Xinyue Liu· International Conference on...· 0 citations
GPE-YOLO is proposed, a robust detection framework built upon the YOLOv11 architecture that explicitly integrates multiscale edge priors to enhance feature resilience and validate the potential of GPE-YOLO for reliable deployment in real-world adverse weather scenarios.
Xiaojie Chen, Yi-Fei Zhou, Yi-Ming Zhou et al.· International Conference on...· 0 citations
RadioTrace is proposed, a novel RM estimation framework without deployment-time fine-tuning that tightly integrates sparse RSS measurements with a frozen pre-trained diffusion prior and achieves competitive performance with state-of-the-art learning-based methods under random sampling, and maintains strong reconstruction quality under restricted-area sampling.
Liu Yang, Qiang Li, Zhuo Cao et al.· IEEE Transactions on Wireles...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
