logo
ProjectOngoing

Learning Generative 3D Scene Models for Training and Validating Intelligent Systems

The status, timeline and source of this project. A free account opens every field.

Source: EU Funding & Tenders Portal

Recently, the field of computer vision has witnessed a major transformation away from expert designed shallow models towards more generic deep representation learning. However, collecting labeled data for training deep models is costly and existing simulators with artist-designed scenes do not provide the required variety and fidelity. Project LEGO-3D will tackle this problem by developing probabi

Status
Under Construction
Sector
Automotive
Location
Germany
Updated
22 Jul 2026
Source
EU Funding & Tenders Portal

ConstructChat

Ask ConstructChat about Learning Generative 3D Scene Models for Training and Validating Intelligent Systems

Pick a question to edit it, or write your own.

First answer free · no account

I am a

Project Information FAQ

Project Information

3 Q
The project “Learning Generative 3D Scene Models for Training and Validating Intelligent Systems” is an infrastructure initiative in the Automotive sector, located in Germany. Taiyo aggregates data on it from EU Funding & Tenders Portal.

Participants

Not available for this record.

Status

Original status

ongoing

Taiyo status

Under Construction

Taiyo last update

2026-07-22

Contact

Not available for this record.

Description

Description

Recently, the field of computer vision has witnessed a major transformation away from expert designed shallow models towards more generic deep representation learning. However, collecting labeled data for training deep models is costly and existing simulators with artist-designed scenes do not provide the required variety and fidelity. Project LEGO-3D will tackle this problem by developing probabilistic models capable of synthesizing 3D scenes jointly with photo-realistic 2D projections from arbitrary viewpoints and with full control over the scene elements. Our key insight is that data augmentation, while hard in 2D, becomes considerably easier in 3D as physical properties such as viewpoint invariances and occlusion relationships are captured by construction. Thus, our goal is to learn the entire 3D-to-2D simulation pipeline. In particular, we will focus on the following problems: (A) We will devise algorithms for automatic decomposition of real and synthetic scenes into latent 3D primitive representations capturing geometry, material, light and motion. (B) We will develop novel probabilistic generative models which are able to synthesize large-scale 3D environments based on the primitives extracted in project (A). In particular, we will develop unconditional, conditioned and spatio-temporal scene generation networks. (C) We will combine differentiable and neural rendering techniques with deep learning based image synthesis, yielding high-fidelity 2D renderings of the 3D representations generated in project (B) while capturing ambiguities and uncertainties. Project LEGO-3D will significantly impact a large number of application areas. Examples include vision systems which require access to large amounts of annotated data, safety-critical applications such as autonomous cars that rely on efficient ways for training and validation, as well as the entertainment industry which seeks to automate the creation and manipulation of 3D content.

Location

Country

Germany

Source

Source

EU Funding & Tenders Portal

URL

More Details

Record type

Project

Sector

Automotive

Article published date

2026-02-01

More on this project

Research

Free account

View all details

You are reading the public part. A free account opens the rest:

  • Every detail on this project
  • News and media coverage
  • Technical research
View all details

Free account · no card · lands you back on this project