search

goutamgmb / deep-rep

Official implementation of Deep Reparametrization of Multi-Frame Super-Resolution and Denoising
Other
56 stars 10 forks source link

Why the reported results of DBSR in your paper are different from the official ones? #1

Closed greatlog closed 2 years ago

greatlog commented 2 years ago

The results of DBSR reported in your paper are slightly higher than that reported in the CVPR2021's paper. Do you re-train the models or use different ways to calculate the metrics?

goutamgmb commented 2 years ago

Yes, we re-trained the DBSR model using the same training parameters as our proposed approach. That is, we trained the model using 4 GPUs, using a larger batch size (16), with a burst size of 14 during training. Furthermore model was trained for 500 epochs. See section 5.1 in our iccv paper for details.