Crack Segmentation for Low-Resolution Images using Joint Learning with Super-Resolution
This paper proposes a method for crack segmentation on low-resolution images. Detailed cracks on their high-resolution images are estimated by super resolution from the low-resolution images. Our proposed method optimizes super-resolution images for the crack segmentation. For this method, we propose the Boundary Combo loss to express the local details of the crack. Experimental results demonstrate that our method outperforms the combinations of other previous approaches.
PDF AbstractCode
Datasets
Khanhha's dataset
Results from the Paper
Ranked #1 on
Crack Segmentation
on khanhha's dataset - 4x upscaling
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Crack Segmentation | khanhha's dataset - 4x upscaling | CSSR (SS→SR) | IoU_max | 0.558 | # 2 | ||
| Average IOU | 0.558 | # 1 | |||||
| Crack Segmentation | khanhha's dataset - 4x upscaling | CSSR (SR→SS) | IoU_max | 0.587 | # 1 | ||
| Average IOU | 0.518 | # 2 | |||||
| Crack Segmentation | khanhha's dataset - 4x upscaling (blind) | CSSR (w/ PSPNet) | IoU_max | 0.557 | # 3 | ||
| Average IOU | 0.539 | # 3 | |||||
| AHD95 | 24.74 | # 5 | |||||
| HD95_min | 21.20 | # 5 |
