Raoul de Charette

48 rue Barrault, 75013 Paris, France.

Welcome. I’m a Research Director in computer vision at Inria Paris, where I lead the Astra-Vision group, within the ASTRA team. My Habilitation (HDR) was completed in 2022, and my PhD in 2012 from Mines Paris. I worked in Carnegie Mellon Uni. (2011), Mines Paris (2013), and Uni. of Makedonia (2014). Beside research, I serve in most venues of the field as area chair (CVPR, ECCV, WACV, IROS) and co-organized or co-founded events like ACVSS, CVPR workshops, WSCV, Indaba, etc. I am also an ELLIS member and a PR[AI]RIE-PSAI Fellow.

My research interest lies in robust and interpretable visual scene understanding.

Email: R.C@inria.fr (replace R with raoul, C with de-charette)

New PR[AI]RIE PhD position on Simulatable Physics-aware World Models (deadline: 17/05/2026)

Soon opening a PostDoc. Got a strong record track in top-tier venues (CVPR,ICCV,ECCV,NeurIPS,ICML,ICLR)? Contact me.

New PR[AI]RIE PhD position on Physics-Grounded Vision Foundation Models.

I'm always looking for talented students, and have regular PhD, Postdoc or intern positions opened. Feel free to email me with a resume + 2 references.

news

2026.11	Co-organizing the Workshop Grounded 4D Multimodal World Models for Autonomous Driving Decision Making at CoRL 2026. Check our Challenges and Call for paper.
2026.07	Outstanding reviewer of ECCV 26.
	Co-organizing the 3rd African Computer Vision Summer School with amazing speakers like David Forsyth, Max Welling, Deepti Ghadiyaram, Amir Zamir, etc.
2026.04	Happy to have Seamie Hayes for a 6-month PhD visit. Welcome Seamie.
2025.11	Welcoming new members in the group: Fatima Baldé and Antonios Tragoudaras starting a PhD, Radu Beche for a PhD visit and Sebastian Cavada as visitor and collaborator.

Students

Fatima Balde
PhD student
co-supervised with Alexandre Boulch (Valeo.ai)

Mohammad Fahes
PhD student
co-supervised with Tuan-Hung Vu, Andrei Bursuc (Valeo.ai) and Patrick Pérez (Kyutai).
2025: Intern at Google DeepMind.

Tetiana Martyniuk
PhD student
co-supervised with Alexandre Boulch, Gilles Puy, Renaud Marlet (Valeo.ai)

Antonios Tragoudaras
PhD student
co-supervised with Tuan-Hung Vu, Andrei Bursuc (Valeo.ai)

Radu Beche
PhD visit

Seamie Hayes
PhD visit

Sebastian Cavada
Visitor

Selected publications

NewtPhys: Do Foundation Models Understand Newtonian Physics?

Sebastian Cavada, Soumava Paul, Tuan-Hung Vu, Andrei Bursuc, and Raoul de Charette

In arXiv, 2026

Bib Project page PDF Code

@inproceedings{newtphys2026,
  title = {NewtPhys: Do Foundation Models Understand Newtonian Physics?},
  author = {Cavada, Sebastian and Paul, Soumava and Vu, Tuan-Hung and Bursuc, Andrei and de Charette, Raoul},
  booktitle = {arXiv},
  year = {2026},
}

PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness

Anh-Quan Cao, Angela Dai, and Raoul de Charette

In CVPR, 2024

Oral, Best paper award Candidate

Bib Project page PDF Code

Oral, Best paper award Candidate

@inproceedings{cao2023pasco,
  author = {Cao, Anh-Quan and Dai, Angela and {de Charette}, Raoul},
  title = {PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness},
  booktitle = {CVPR},
  year = {2024},
}

Material Palette: Extraction of Materials from a Single Image

Ivan Lopes, Fabio Pizzati, and Raoul de Charette

In CVPR, 2024

Bib Project page PDF Code

@inproceedings{lopes2023material,
  author = {Lopes, Ivan and Pizzati, Fabio and {de Charette}, Raoul},
  title = {Material Palette: Extraction of Materials from a Single Image},
  booktitle = {CVPR},
  year = {2024},
}

PODA: Prompt-driven Zero-shot Domain Adaptation

Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, and Raoul de Charette

In ICCV, 2023

Bib Project page PDF Code

@inproceedings{fahes2022poda,
  author = {Fahes, Mohammad and Vu, Tuan-Hung and Bursuc, Andrei and P{\'e}rez, Patrick and {de Charette}, Raoul},
  title = {PODA: Prompt-driven Zero-shot Domain Adaptation},
  booktitle = {ICCV},
  year = {2023},
}

All publications >>>