search

shunsukesaito / PIFu

This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"
https://shunsukesaito.github.io/PIFu/
Other
1.76k stars 340 forks source link

Restriction on input image size #2

Closed usamahjundia closed 4 years ago

usamahjundia commented 4 years ago

Seems like there is a slight restriction on input image size. When i input an image with size not equal to 512 x 512 (could be smaller, could be larger), i got the the size of tensor a (blablabla) must match the size of tensor b (blablabla) at non singleton dimension blablabla

So is there a restriction for input shape?

shunsukesaito commented 4 years ago

The hourglass network expects the input resolution to be a multiple of 32 and the model is trained with 512 x 512. I recommend resizing images to 512 x 512. For other resolutions, I wouldn't expect any good results.

usamahjundia commented 4 years ago

i see, that clears things up, thanks!