Zero-shot Monocular Scene Flow (ZeroMSF)

Closed weights NVIDIA,Brown University January 2025

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
NVIDIA,Brown University
Organisation type
Industry,Academia
Country
United States of America
Published
20 January 2025
Authors
Yiqing Liang, Abhishek Badki, Hang Su, James Tompkin, Orazio Gallo

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
3D modeling, Driving
Task
3D reconstruction, Self-driving car

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Training data
tokens

"1M annotated training samples across diverse synthetic scenes"

Epochs
50

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
3.2 × 10¹⁹ FLOP

312000000000000 FLOP / GPU / sec * 8 GPUs * 12 hours * 3600 sec / hour * 0.3 [assumed utilization] = 3.234816e+19 FLOP

How it was established
Hardware

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA A100
Chips used
8
Wall-clock time
12 hours

"All experiments are trained with 8 NVIDIA A100 GPUs for 50 epochs, which take 12 hours."

Power draw
6.3 kW

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

"Code coming!" [July 2025 - still no release]

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
Zero-Shot Monocular Scene Flow Estimation in the Wild
Last updated
11 February 2026

What the numbers mean

Background

Zero-shot Monocular Scene Flow (ZeroMSF) was published by NVIDIA,Brown University, in United States of America, in January 2025. It comes out of industry,Academia.

It works in 3D modeling, Driving, and is recorded as doing 3D reconstruction, Self-driving car.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

The training run consumed about 3.2 × 10¹⁹ FLOP, on NVIDIA A100. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

Answers

Zero-shot Monocular Scene Flow (ZeroMSF) — common questions

01

When was Zero-shot Monocular Scene Flow (ZeroMSF) released?

Zero-shot Monocular Scene Flow (ZeroMSF) was published in January 2025.

02

What is Zero-shot Monocular Scene Flow (ZeroMSF) used for?

Zero-shot Monocular Scene Flow (ZeroMSF) works in 3D modeling, Driving, and is recorded as handling 3D reconstruction, Self-driving car. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

03

How much compute was used to train Zero-shot Monocular Scene Flow (ZeroMSF)?

Around 3.2 × 10¹⁹ FLOP, on NVIDIA A100. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

04

What GPU do I need to run Zero-shot Monocular Scene Flow (ZeroMSF)?

None. Zero-shot Monocular Scene Flow (ZeroMSF) is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

05

Is Zero-shot Monocular Scene Flow (ZeroMSF) open source?

No. Zero-shot Monocular Scene Flow (ZeroMSF) has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does Zero-shot Monocular Scene Flow (ZeroMSF) have?

No parameter count has been published for Zero-shot Monocular Scene Flow (ZeroMSF), which is why no memory or speed figure appears on this page.

07

Who created Zero-shot Monocular Scene Flow (ZeroMSF)?

Zero-shot Monocular Scene Flow (ZeroMSF) was published by NVIDIA,Brown University, based in United States of America, categorised as industry,Academia.

Source

Original publication

Record last updated 11 February 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.