AI models
3DMM-CNN
Parameters
44.5M
Published
Dec 15, 2016
3DMM-CNN is an AI model developed by University of Southern California (United States), first published in December 2016. It works in the vision domain, on tasks such as face recognition and 3d reconstruction.
Epoch AI has no training-compute estimate for this model. The model has 44,500,000 parameters. It was trained on roughly 500K datapoints. Training ran on 1 NVIDIA GeForce GTX 590.
Access: Open weights (restricted use). Its weights are openly available. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- University of Southern California
- Country of organization
- United States
- Domain
- Vision
- Task
- Face recognition, 3D reconstruction
- Parameters
- 44,500,000
- Dataset size
- 500K
- Training hardware
- NVIDIA GeForce GTX 590
- Chips used
- 1
- Training power draw
- 421 W
- Model accessibility
- Open weights (restricted use)
- Open weights
- Yes
- Epoch confidence
- Confident
More from University of Southern California
SourceEpoch AI, 'AI Models'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/ai-models. Licensed under CC BY 4.0.
← All ai models