vt and face information of the prediction result

[juch001]

Hi,

If change the prediction output as .obj files, how would I create the vt and f information inside the .obj file? Please kindly send me examples/templates of each garment if you have them.

Besides, is there a way to change the number of the vertices and faces for prediction output. Thank you so much.

Best Regards, JC

[chaitanya100100]

Neural network works on a fixed output dimension. So there is no way to change the number of vertices and faces in the output. We take our template from MGN(https://github.com/bharat-b7/MultiGarmentNetwork) which comes with those texture coordinates. So you should look into that. You can export obj with textures like this:

v = f = ft = vt =

ms = Mesh(v=v, f=f, vt=vt, ft=ft) ms.save_obj("result.obj")

[juch001]

thank you.

[juch001]

Hi,

Could you please advise what the 'ft' is? I went through the documents inside the link and only found vt and f but not ft. Thanks.

Best Regards, JC

On Sun, May 23, 2021 at 12:40 PM Chaitanya Patel @.***> wrote:

Neural network works on a fixed output dimension. So there is no way to change the number of vertices and faces in the output. We take our template from MGN( https://github.com/bharat-b7/MultiGarmentNetwork) which comes with those texture coordinates. So you should look into that. You can export obj with textures like this:

v = f = ft = vt =

ms = Mesh(v=v, f=f, vt=vt, ft=ft) ms.save_obj("result.obj")

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/chaitanya100100/TailorNet/issues/36#issuecomment-846500931, or unsubscribe https://github.com/notifications/unsubscribe-auth/AQ6R4WKBOBRXXXTMUNC5OYTTPCBLNANCNFSM45KYBD7Q .

[chaitanya100100]

Answered here: https://github.com/chaitanya100100/TailorNet/issues/37