Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

Learning Visual Foundation Models for Perceiving 3D Humans

Project description

Towards generalisable 3D human understanding in open-world AI

The rapid growth of AI and the integration of large language model (LLM) technologies across a wide variety of services and applications have underscored the need for improved visual learning and sensor solutions for the future of AI. The complexity, dynamism, and depth of environments, as well as human motion and behaviour, make this a distinctly difficult task, leading most methods to struggle in open-world settings where they need to generalise beyond domain-specific training data. The ERC-funded Human3D project will develop and research generalisable visual representations from large-scale training data, followed by the creation of a foundation model for supporting human analysis and modelling tasks in 3D environments in open-world settings.

Objective

The world is entering the age of autonomy, where systems like self-driving cars and assistive robots face the challenge of perceiving and understanding human behavior in complex, dynamic environments through sensory inputs like images. While human motion and behavior have been studied extensively using visual data, existing methods often struggle in open-world settings due to their inability to generalize beyond domain-specific training data. The goal of this project is to learn generalizable visual representations from large-scale training data and create a foundational model that supports various human analysis and modeling tasks, grounded in 3D environments, in an open-world setting. Our key objectives include (1) Devising new human-centric representations and algorithms for accurate 3D human motion and appearance reconstruction from in-the-wild videos. (2) Developing advanced generative models synthesizes large-scale, realistic virtual humans, emphasizing controllability and efficiency. (3) Designing physics-guided methods for long-duration human-scene interaction capture using embodied devices. (4) Studying efficient learning algorithms and unified model architectures for 3D human foundation models that enable efficient fine-tuning and generalization across various human-centric computer vision tasks. We aim to establish the computational and algorithmic groundwork for human-centric visual foundation models, with advancement in generative modeling, human-centric representation learning, and visual data simulation. Our work will facilitate the development of autonomous AI agents for various sectors, including autonomous driving, extended reality, education, and manufacturing. Ultimately, this project is committed to advancing human-centric AI technologies, fostering more robust and effective human-AI interaction, and paving the way for practical applications that significantly improve everyday life and industrial processes.

Fields of science (EuroSciVoc)

Keywords

Programme(s)

Topic(s)

Funding Scheme

HORIZON-ERC - HORIZON ERC Grants

See all projects funded under this funding scheme

Call for proposal

(opens in new window) ERC-2025-STG

See all projects funded under this call

Host institution

EIDGENOESSISCHE TECHNISCHE HOCHSCHULE ZUERICH
Net EU contribution
€ 1 500 000,00
Address
Raemistrasse 101
8092 Zuerich
Switzerland
Region
Schweiz/Suisse/Svizzera Zürich Zürich
Activity type
Higher or Secondary Education Establishments
Links
Total cost
€ 1 500 000,00

Beneficiaries (1)