jmfacil
commented
2 years ago These points are addressed in the paper.
On Thu, Mar 10, 2022 at 7:17 PM Shuai Peng @.***> wrote:
From the results of your paper, I find that the network constructed by Equirectangular Convolutions (EquiConvs) has no great improvement in indicators compared with the network constructed by traditional convolution (StdConvs). How can you explain the benefits of EquiConvs in processing ERP projection images?
In addition, the computation time of the network constructed by EquiConvs is 10 times that of the network constructed by StdConvs. So what are the advantages of EquiConvs compared to StdConvs?
— Reply to this email directly, view it on GitHub https://github.com/cfernandezlab/CFL/issues/32, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACV4PPIFXZC6J653P2URH5TU7K3NDANCNFSM5QOOCHFQ . You are receiving this because you are subscribed to this thread.Message ID: @.***>
--
José M. Fácil Ph.D. Student in Computer Vision Website: http://webdiis.unizar.es/~jmfacil/ University of Zaragoza, Spain
From the results of your paper, I find that the network constructed by Equirectangular Convolutions (EquiConvs) has no great improvement in indicators compared with the network constructed by traditional convolution (StdConvs). How can you explain the benefits of EquiConvs in processing ERP projection images?
In addition, the computation time of the network constructed by EquiConvs is 10 times that of the network constructed by StdConvs. So what are the advantages of EquiConvs compared to StdConvs?