GAN-PD: generative adversarial networks for fabric defect generation towards precise detection
Yuyang Xia, Yong Yin, Fengkai Luan, Junqi Liu, Jiaxing Yang · 2026
Read GAN-PD: generative adversarial networks for fabric defect generation towards precise detection by Yuyang Xia, Yong Yin, Fengkai Luan, Junqi Liu, Jiaxing Yang (2026) 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-13381523.txt.
Description
Yuyang Xia and co-authors published an engineering paper in 2026 on making fake fabric faults with computer models so real faults are easier to spot. Real fault samples are scarce, and thin scratches are hard to catch yet matter for cloth grading. Older generators chase lifelike images but lose the long, unbroken shape of real faults. The team built a system aimed at detection, not just looks.
Their system, called GAN-PD, uses parts that focus on fault-relevant detail and enforce line flow along the fault. Tests on a benchmark cloth dataset gave sharper thin faults and smoother blending with the weave. Detectors trained with the fake faults found real ones more accurately than with rival generators.
Catalog record
| CREATOR | Yuyang Xia, Yong Yin, Fengkai Luan, Junqi Liu, Jiaxing Yang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 117 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |