search

sniklaus / 3d-ken-burns

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch
Other
1.52k stars 225 forks source link

Benchmark results #23

Closed dfrumkin closed 4 years ago

dfrumkin commented 4 years ago

You write that "the depth boundary error is currently different from the paper". I see that the huge dbe_com can be ignored; however, there are noticeable differences in some other metrics as well. Do you know why?

abs_rel =  0.09667361210538511
sq_rel  =  0.08968517555964581
rms     =  0.468931547303287
log10   =  0.04028934128953222
thr1    =  0.9042070992913529
thr2    =  0.9735211480731727
thr3    =  0.9914000487947728
dde_0   =  0.9348635887380082
dde_m   =  0.02829501122683011
dde_p   =  0.0368414000351617
dbe_acc =  2.027432278515633
dbe_com =  29.32951945280528
pe_fla  =  2.1928497290019897
pe_ori  =  10.243341646515104
sniklaus commented 4 years ago

Would you mind clarifying what the issue is? Aside from the depth boundary error, which is expected to differ, all other metrics match exactly what we report in our paper?

dfrumkin commented 4 years ago

You are right. I got confused because I looked at NYU v2 metrics... Thanks a lot!