Photo-Geometric Autoencoder

Published

Nov 25, 2019

Photo-Geometric Autoencoder is an AI model developed by University of Oxford (United Kingdom), first published in November 2019. It works in the 3d modeling and vision domain, on tasks such as 3d reconstruction.

Epoch AI has no training-compute estimate for this model. It was trained on roughly 819.2M datapoints.

Access: Open weights (unrestricted). Its weights are openly available. The reference paper has 338 citations.

Full record

Organization: University of Oxford
Country of organization: United Kingdom
Domain: 3D modeling, Vision
Task: 3D reconstruction
Dataset size: 819.2M
Model accessibility: Open weights (unrestricted)
Open weights: Yes
Citations: 338