search

hli1221 / imagefusion-rfn-nest

RFN-Nest(Information Fusion, 2021, Highly Cited Paper) - PyTorch =1.5，Python=3.7
108 stars 18 forks source link

question in page10 #2

Closed songxujay closed 1 year ago

songxujay commented 3 years ago

Hello Dr.Li:

It's very happy to study your work, but I have a question about the details in Page10. In page10, you described the ablation study with the metric indices (MI, FFMIdct , FFMIw, EN, SD, VIF), but in table3, I didn't see the indices about FFMIdct , FFMIw and VIF.

I dont know if my understand this part fully, please help me, thank you!.

Best Regards.

hli1221 commented 3 years ago

I am very sorry about this clerical error. Actually, this part "With the nest connection, the decoder is able to preserve more image information conveyed by the multiscale deep features (𝑀𝐼, 𝐹 𝐹𝑀𝐼𝑑𝑐𝑑, 𝐹 𝐹𝑀𝐼𝑀) and generate more natural and clearer fused image (𝐸𝑁, 𝑆𝐷, 𝑉 𝐼𝐹)." should change to "With the nest connection, the decoder is able to preserve more image information conveyed by the multiscale deep features (𝑀𝐼, Nabf, MS-SSIM) and generate more natural and clearer fused image (𝐸𝑁, 𝑆𝐷, SCD)." Thank you very much to point out this mistake in our paper.