wuanran

Thanks for you interest in our work. Our metric calculation (PSNR) is implemented in the same manner as common SR benchmarks. Specifically, on the Set5 X4 dataset, we first downscale...

Thank you very much for your reminder. We indeed missed the definition of the eval_type parameter in "test-set5-4.yaml" when we open-sourced it. We retested the results on Set5 X4 and...

The image you output does have differences from ours. This is the result after we applied super-resolution using ContinuousSR. [output_ContinuousSR.zip](https://github.com/user-attachments/files/19823360/output_ContinuousSR.zip)

Thank you for your interest in our work! Did you load the pre-trained model for the backbone during the training process? We found in our experiments that whether to load...

Did you obtain the LR data from the GT using the bicubic method? If there are other types of degradations, such as blur, using our pre-trained model may not yield...

Thank you for your interest in our work! We followed the method in GaussianImage to transform images into Gaussian kernel parameters. The detailed optimization process (including covariance parameterization and loss...

> 作者您好，有两个问题希望请教一下： （1） ”weighted_cholesky = para_ / 4; weighted_cholesky[:, 0] *= scale2; weighted_cholesky[:, 1] *= scale2; weighted_cholesky[:, 2] *= scale1”这几行代码的逻辑是什么？在正文中似乎并没有对应的解释。 （2）正文中写到"σ_x^2 , σ_y^2 , and ρσ_x_σy fall within the ranges...

Thanks for your interest in our work! We also conducted experiments on the EDSR and RDN backbones and achieved good performance. However, since the experiments were completed within the company,...

Thank you for your interest in our work! The training config files will be released right after our paper is accepted. As for the pretrained weights — they refer to...

您好，确实是没有用到的