reshow

> > > Puzzled to 3d NME, too. I cannot find an explicit statement... The paper of 3D-FAN gives a formula of NME. I just cannot get the same 3D...

Sorry, I forgot to upload some files. I upgrade the repository. You can fetch it, or just download the files in uv-data and delete the code of reading mean_uv_posmap.npy (this...

If you run the code directly and correctly, the result would be slightly worse than mine (2d landmark nme is about 3.30±0.03 ) since the number of parameters is less...

How about the NME on training data?

Sorry, I mean the printed 'metrics0' of training dataset and evaluation dataset

I didn't try it. There are some differences between our generation codes but I don't think they will affect the performance. The metrics0 should reach 0.03 in less than 10...

> > > > I didn't try it. There are some differences between our generation codes but I don't think they will affect the performance. > > The metrics0 should...

> > > It is my email: [[email protected]](mailto:[email protected]) . I've updated it. Sorry for the trouble.

> > > > > It is my email: [[email protected]](mailto:[email protected]) . > > > > > > I've updated it. Sorry for the trouble. > > I'm sorry to bother...

> > > > > It is my email: [[email protected]](mailto:[email protected]) . > > > > > > I've updated it. Sorry for the trouble. > > I'm sorry to bother...