reproduction of training code

[Oak777]

Hi, thanks for your work! I reproduced the training code based on GaussianSR, but the model weights I trained did not perform as well as expected.

Note: The left image shows the results using your provided weights, which perform better, and the right image shows the results using my trained weights.

[peylnog]

Thank you for your reproduction and interest in our work. We plan to release the training code as soon as the paper is officially accepted. Internally, we have retrained the model multiple times, and both the performance and visual results are fully consistent with those reported in the paper.

We kindly ask for your patience. If you are interested in further discussion or collaboration, feel free to reach out via WeChat: 17370780725 or email: [email protected].

[PuPuuu]

Hi, thanks for your work! I reproduced the training code based on GaussianSR, but the model weights I trained did not perform as well as expected.

Note: The left image shows the results using your provided weights, which perform better, and the right image shows the results using my trained weights.

Hello, is it convenient for me to contact you to discuss the code reproduction issue of the paper?

[peylnog]

Hi, thanks for your work! I reproduced the training code based on GaussianSR, but the model weights I trained did not perform as well as expected. Note: The left image shows the results using your provided weights, which perform better, and the right image shows the results using my trained weights.

Hello, is it convenient for me to contact you to discuss the code reproduction issue of the paper?

Absolutely no problem — feel free to add our contact information! We welcome more communication and collaboration. Looking forward to staying in touch!