
Academic lab · Lausanne, Switzerland
VITAEPFL
EPFL's lab on socially aware AI for transportation, with open pose and trajectory code.
Lausanne, Switzerland
- Type
- Academic lab
- Based in
- Lausanne, Switzerland
- Key papers
- 1
- Featured projects
- 4
About
VITA, the Visual Intelligence for Transportation lab, is led by Alexandre Alahi at EPFL, where he joined in 2017. It works on socially aware AI for safe autonomous systems and mobility.
Its open code includes OpenPifPaf for human pose estimation, which was combined with commercial licensing for technology transfer, along with trajectory prediction and video generation projects on GitHub.
Mission and ambitionsThe lab makes AI socially aware for transportation.
Known for
- 01
Socially aware AI
- 02
Human motion prediction
Milestones
- 2017
Alahi joins EPFL
Start of lab leadership.
- 2022
OpenPifPaf technology transfer
Open-source pose estimation tool paired with commercial licenses.
- 2021
Editor's choice award
Image and Vision Computing, for human motion prediction.
- 2023
TEDx talk on socially aware AI
Public outreach on the lab's research.
Open source
[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling (2,622 stars)
[ICRA] Crowd-aware Robot Navigation (742 stars)
A Unified Framework for scalable Vehicle Trajectory Prediction, ECCV 2024 (493 stars)
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and bo (462 stars)
Research papers
Notable releases
Openness
Research code is public on GitHub for most papers.
People
- Alexandre AlahiHead of lab
Listed from the lab's own pages and public profiles.
Contact and community
Contact via site.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



