qibao77
qibao77
> @yoon28 That's true. I implemented the paper using KernelGAN to estimate kernel and create a kernel pool, then using the ESRGAN to train paired images. However, my results is...
> @JimXiongGM 如果这个方法再和一些传统的Blind Deblur方法结合，先估计出模糊核再套到这个流程里来，会不会可以哦？ 作者在paper中有说，可以用别的方法估个核，再带到方法中。
Thank you for your reply!
> Adding the KL loss for latent codes is only used to validate the effects of loss functions in my exps, e.g., jointing gan loss and the KL loss, but...
I am sorry for the late reply. 1) For JPEG image deblocking task, we set the input and output channels to 1 for fair comparison with other methods. You can...
您好，由于我做的一个项目只用到了角点检测部分，因此暂时不会实现提取标定板的部分，如果你有兴趣实现欢迎一起交流。
嗯嗯，谢谢~
I‘m sorry for late reply, has your problem been solved? I ran the code again in the denoising task, no problem. Can you provide more details?
Thank you for your attention. I am busy with another work, so I expect to update the code at the end of the year. I am sorry for the slow...
Yes. In training step 1, we keep α_in= 0, while in training step 2, we keep α_in = 1. I am sorry for the late reply.