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
1.75k stars 343 forks source link

Multi-views BUG #119

Open caiyongqi opened 2 years ago

caiyongqi commented 2 years ago

When I set num_views=2: File "/home/user/cyq/3D/PIFu/lib/model/HGPIFuNet.py", line 110, in query pred = in_img[:, None].float() * self.surface_classifier(point_local_feat) RuntimeError: The size of tensor a (4) must match the size of tensor b (2) at non-singleton dimension 0

kampelmuehler commented 2 years ago

https://github.com/shunsukesaito/PIFu/issues/3#issuecomment-592040217

Multi-view is not supported by this repo.

caiyongqi commented 2 years ago

Thanks.