Skip to content

Photo-Geometric Autoencoder

University of Oxford3D reconstructionOpen weights

Photo-Geometric Autoencoder is a 3d reconstruction model from University of Oxford released in 2019.

About Photo-Geometric Autoencoder

We propose a method to learn 3D deformable object categories from raw single-view images, without external supervision. The method is based on an autoencoder that factors each input image into depth, albedo, viewpoint and illumination. In order to di

Details

Provider
University of Oxford
Task
3D reconstruction
Released
2019-11-25
Open weights
Yes
View model source

Explore

FAQ