Mono3D++

Closed weights University of California Los Angeles (UCLA),Megvii Inc January 2019

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
University of California Los Angeles (UCLA),Megvii Inc
Organisation type
Academia,Industry
Country
United States of America, China
Published
11 January 2019
Authors
Tong He, Stefano Soatto

What it does

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

Domain
3D modeling, Vision
Task
3D segmentation, Object detection

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

"We evaluate our method on the KITTI object detection benchmark. This dataset contains 7, 481 training images "

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
4.9 × 10¹⁸ FLOP

(4) * (6.691 * 10**12) * (168* 3600) * (0.3) = (num gpu) * (peak flops) * (time in seconds) * (assumed utilization rate) = training time - about one week = 168 hours from "It takes about one week to train the 2D bounding box net-work, and two hours for the orientation/3D scale network on KITTI with 4 TITAN-X GPUs. The landmark detector is trained on Pascal3D. The training process for the monocu- lar depth estimation network is unsupervised using KITTI stereo-pairs, which takes around 5 to 12 …

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 GeForce GTX TITAN X
Chips used
4
Chip-hours
672
Wall-clock time
168 hours (7 days)

"about one week" from section 3.4

Power draw
2.1 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

How it is classified

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

Record confidence
Confident
Citations
135

Sources

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

Reference
Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors
Last updated
25 May 2026

What the numbers mean

What this model is

Mono3D++ was published by University of California Los Angeles (UCLA),Megvii Inc, in the country recorded as United States of America, during January 2019. The category the publisher falls under is academia,Industry.

It works in the domain of 3D modeling, Vision, and is recorded as performing the task of 3D segmentation, Object detection.

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

Training and provenance

Training it took a computation budget of roughly 4.9 × 10¹⁸ FLOP, on hardware recorded as NVIDIA GeForce GTX TITAN X. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

Mono3D++ — common questions

01

Mono3D++— how much compute was used to train it?

Training consumed around 4.9 × 10¹⁸ FLOP, on hardware recorded as NVIDIA GeForce GTX TITAN X. 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.

02

Mono3D++— what GPU do I need to run it?

None. This 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.

03

Mono3D++— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

04

Mono3D++— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

05

Mono3D++— who created it?

It was published by University of California Los Angeles (UCLA),Megvii Inc, based in United States of America, an organisation categorised as academia,Industry.

06

Mono3D++— when was it released?

It was published in January 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

07

Mono3D++— what is it used for?

It works in the domain of 3D modeling, Vision, and is recorded as handling the task of 3D segmentation, Object detection. 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.

Source

Original publication

Record last updated 25 May 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.