AI models
Zero-shot Monocular Scene Flow (ZeroMSF)
Training compute
3.2×10¹⁹ FLOP
Published
Jan 20, 2025
Zero-shot Monocular Scene Flow (ZeroMSF) is an AI model developed by NVIDIA and Brown University (United States), first published in January 2025. It works in the 3d modeling and driving domain, on tasks such as 3d reconstruction and self-driving car.
Training it took an estimated 3.2×10¹⁹ FLOP of compute (estimation method: hardware). Training ran on 8 NVIDIA A100 for about 12 hours.
Access: Unreleased. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.
Full record
- Organization
- NVIDIA, Brown University
- Country of organization
- United States
- Domain
- 3D modeling, Driving
- Task
- 3D reconstruction, Self-driving car
- Training compute
- 3.2×10¹⁹ FLOP
- Compute estimation method
- Hardware
- Training hardware
- NVIDIA A100
- Chips used
- 8
- Training time
- 12 h
- Training power draw
- 6.3 kW
- Model accessibility
- Unreleased
- Open weights
- No
- Epoch confidence
- Confident
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