An Improved Generative Adversarial Network-Based and U-Shaped Transformer Method for Glass Curtain Crack Deblurring Using UAVs
Jiaxi Huang, Guixiong Liu, Vittorio M N Passaro · 2024
Read An Improved Generative Adversarial Network-Based and U-Shaped Transformer Method for Glass Curtain Crack Deblurring Using UAVs by Jiaxi Huang, Guixiong Liu, Vittorio M N Passaro (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11644981.txt.
Description
Jiaxi Huang and co-authors sharpen drone photos of cracked glass facades, in a 2024 paper. Drones inspect high glass curtain walls for cracks, a key safety task. Shaking and weather blur their shots, which hides fine cracks. Their network, GlassCurtainCrackDeblurNet, restores those images before crack hunting begins.
The design pairs an adversarial network with an improved U-shaped transformer. The team also built a dedicated data set of blurred and clean facade crack photos for training. On that set and a standard action-camera benchmark, their method beat established deblurring tools on both look and scores. Clearer drone images mean earlier, safer detection of facade damage on tall buildings worldwide.
Catalog record
| CREATOR | Jiaxi Huang, Guixiong Liu, Vittorio M N Passaro |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 43 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |