Research map / Image generation / Image restoration
Multi-Window Gabor Transform Network for Ground Penetrating Radar B-Scan Image Reconstruction
Huabin Wang, Yu Yang, Xinran Zhong, Zilong Ling
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add defect guidance network and guidance loss to baseline (ablation) | U-Net baseline · GRD (GPR B-scan reconstruction) | SSIM (%): 67.93 -> 71.05 | Improved |
| add defect guidance network and guidance loss to baseline (ablation) | U-Net baseline · GRD (GPR B-scan reconstruction) | PSNR: 28.02 -> 29.29 | Improved |
| add single-window Gabor transform module to baseline (ablation) | U-Net baseline · GRD (GPR B-scan reconstruction) | SSIM (%): 67.93 -> 75.06 | Improved |
| replace single-window with multi-window Gabor module (ablation) | U-Net baseline · GRD (GPR B-scan reconstruction) | SSIM (%): 67.93 -> 78.59 | Improved |
| replace single-window with multi-window Gabor module (ablation) | U-Net baseline · GRD (GPR B-scan reconstruction) | PSNR: 29.68 -> 30.21 | Improved |
| add defect guidance network to multi-window Gabor model (ablation) | MGT-Net · GRD (GPR B-scan reconstruction) | SSIM (%): 78.59 -> 81.72 | Improved |
| add defect guidance network to multi-window Gabor model (ablation) | MGT-Net · GRD (GPR B-scan reconstruction) | PSNR: 30.21 -> 30.50 | Improved |
| set pixel-loss weight lambda1 to 10 instead of 5 (ablation) | MGT-Net · GRD (GPR B-scan reconstruction) | SSIM (%): 80.99 -> 81.72 | Improved |
| set guidance-loss weight lambda2 to 1 instead of 20 (ablation) | MGT-Net · GRD (GPR B-scan reconstruction) | SSIM (%): 78.83 -> 81.72 | Improved |
| raise pixel-loss weight lambda1 from 10 to 20 (ablation) | MGT-Net · GRD (GPR B-scan reconstruction) | PSNR: 30.50 -> 29.97 | Hurt |
| train detector on MGT-Net reconstructions instead of DN reconstructions | defect detector · GRD defect detection on reconstructed images | IOU: 65.04 -> 66.43 | Improved |
| train detector on MGT-Net reconstructions instead of DN reconstructions | defect detector · GRD defect detection on reconstructed images | BER: 9.39 -> 7.01 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Burstormer — Burstormer: Burst Image Restoration and Enhancement Transformer (CVPR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- EDENet: Echo Direction Encoding Network for Place Recognition Based on Ground Penetrating Radar (AAAI 2025 · similarity 0.81)
- Wavelet and Prototype Augmented Query-based Transformer for Pixel-level Surface Defect Detection (CVPR 2025 · similarity 0.79)
- Auto-Linear Phenomenon in Subsurface Imaging (ICML 2024 · similarity 0.78)
- Deep Linear Array Pushbroom Image Restoration: A Degradation Pipeline and Jitter-Aware Restoration Network (AAAI 2024 · similarity 0.78)
- A Diffusion-Based Framework for Multi-Class Anomaly Detection (AAAI 2024 · similarity 0.78)
- DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection (CVPR 2025 · similarity 0.78)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
