RGB-D Rail Surface Defect Inspection Driven by Conditional Diffusion Architecture and Frequency Knowledge
This project provides source code and results for our IEEE Sensors Journal paper “RGB-D Rail Surface Defect Inspection Driven by Conditional Diffusion Architecture and Frequency Knowledge”.
The saliency maps of all compared methods can be download from [baidu pan fetch code: 94ev]
Our saliency maps and model can be download from [baidu pan fetch code: vowt].