MARS: Radio Map Super-resolution and Reconstruction Method under Sparse Channel Measurements
read the original abstract
Radio maps reflect the spatial distribution of signal strength and are essential for applications like smart cities, IoT, and wireless network planning. However, reconstructing accurate radio maps from sparse measurements remains challenging. Traditional interpolation and inpainting methods lack environmental awareness, while many deep learning approaches depend on detailed scene data, limiting generalization. To address this, we propose MARS, a Multi-scale Aware Radiomap Super-resolution method that combines CNNs and Transformers with multi-scale feature fusion and residual connections. MARS focuses on both global and local feature extraction, enhancing feature representation across different receptive fields and improving reconstruction accuracy. Experiments across different scenes and antenna locations show that MARS outperforms baseline models in both MSE and SSIM, while maintaining low computational cost, demonstrating strong practical potential.
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
RadioDiff-Inv2: Differentiable Diffusion Inversion under Location Drift from Sparse Noisy Measurements for Radio Map Estimation
RadioDiff-Inv2 estimates radio maps from sparse noisy measurements under location drift by making diffusion inversion differentiable via Gaussian resampling and probability-flow ODE optimization.
-
Spatio-Sequential Recurrent Network for 3-D Tunnel Propagation Modeling
UG-SSRNN jointly enhances 2D cross-sections and longitudinal propagation in tunnel EM fields via a convolutional recurrent backbone with prediction-aware upsampling, matching fine-mesh PWE on multiple test cases while...
-
Deep Learning-Based Site-Specific Channel Modeling and Inference
A dual-branch cross-attention neural network with recurrent tracking reconstructs complete channel impulse responses from satellite imagery by predicting TDL parameters, reaching over 0.96 PDP cosine similarity on uns...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.