Nicolas Ugrinovic
nugrinovic@iri.upc.edu

I am a Ph.D. student at IRI under the supervision of Francesc Moreno-Noguer and Alberto Sanfeliu. Previously, I was an Applied Science intern at Amazon Science with Alex Vorobiov. I was also a visitor at Stanford University in Leonidas Guibas Lab and at Naver Labs Europe with Gregory Rogez and Philippe Weinzaepfel. My research is in areas of computer vision and machine learning, specifically on 3D human pose/motion estimation, human motion generation, and reconstruction of 3D bodies.

Email  /  CV  /  Google Scholar  /  GitHub /  LinkedIn  /  Twitter

nicolas_ugrinovic.jpg
News
  • MultiPhys accepted to CVPR 2024!
  • Nov 01, 2023 Started an internship at Amazon Science in Tubingen, Germany!
  • May 01, 2023 Started an internship at Stanford University in Palo Alto, USA!
  • Purposer acceped at 3DV 2024!
  • Jul 01, 2022 Started an internship at NaverLabs Europe in Grenoble, France!
  • DepthSize accepted to 3DV 2021 as an oral presentation!
  • Paper on 3D persons reconstruction accepted to VISAPP 2021 as an oral presentation!
Publications
MultiPhys: Multi-Person Physics-aware 3D Motion Estimation
Nicolas Ugrinovic, Boxiao Pan, Georgios Pavlakos, Despoina Paschalidou, Bokui Shen, Jordi Sanchez-Riera, Francesc Moreno-Noguer, Leonidas Guibas
Computer Vision and Pattern Recognition (CVPR), 2024  
project page / code / bibtex

Using a physics simulator to recover physically plausible multi-person 3D motion.
Purposer: Putting Human Motion Generation in Context
Nicolas Ugrinovic, Thomas Lucas, Fabien Baradel, Philippe Weinzaepfel, Gregory Rogez, Francesc Moreno-Noguer
IEEE International Conference on 3D Vision (3DV), 2024  
project page / code / bibtex

Generating 3D human motion that interacts with a 3D scene.
Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images
Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo, Alberto Sanfeliu, Francesc Moreno-Noguer
IEEE International Conference on 3D Vision (3DV), 2021  (Oral Presentation)
project page / code / bibtex

Estimating multiple 3D people from single monocular RGB images.
Single-view 3D Body and Cloth Reconstruction under Complex Poses
Nicolas Ugrinovic, Albert Pumarola, Alberto Sanfeliu, Francesc Moreno-Noguer
Int. Conf. on Computer Vision Theory and Applications (VISAPP), 2021  (Oral Presentation)
bibtex

Reconstructing 3D humans with garments under complex poses.
Academic Services
  • Serve as reviewer for ECCV, CVPR, ICRA, NeurIPS

Taken from Jon Barron's website.