Nicolas Ugrinovic

I am a Postdoctoral Researcher at Carnegie Mellon University, where I work with Kris Kitani. Previously, I worked at Meta (FAIR).

I obtained my PhD from IRI-UPC under the supervision of Francesc Moreno-Noguer. During this time, I interned at Amazon Science. I was also a visitor at Stanford University in Leonidas Guibas Lab and Naver Labs Europe with Gregory Rogez.

My research is in computer vision and machine learning. I am interested in pushing the boundaries of perception and understanding of our dynamic 3D world by modeling humans and their environment in a physically grounded manner.

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

News

Nov. 2025 Our work SAM 3D Body is now published!
May. 2025 Joined Meta (FAIR) as a Postdoc in Menlo Park, USA!
MultiPhys accepted to CVPR 2024!
Nov. 2023 Started an internship at Amazon Science in Tubingen, Germany!
May. 2023 Visiting researcher at Stanford University in Palo Alto, USA!
Purposer acceped at 3DV 2024!
Jul. 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!

Preprints

	SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image Yu-Rou Tuan, Hao-Tang Tsui, Nicolas Ugrinovic, Kris Kitani, Xiaoxuan Ma arXiv, 2026 paper / project page / code
	Point2Part: Unified 3D Partitioning From Point Prompts Hao-Tang Tsui, Yu-Rou Tuan, Xiaoxuan Ma, Nicolas Ugrinovic, Takaaki Shiratori, Kris Kitani arXiv, 2026 paper / project page / code

Publications

	REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image Xiaoxuan Ma, Jiashun Wang, Nicolas Ugrinovic, Yehonathan Litman, Kris Kitani SIGGRAPH Asia, 2026 paper / project page / code
	Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild Yehonathan Litman, Xiaoxuan Ma, Manan Shah, Nicolas Ugrinovic, Kris Kitani, Fernando De la Torre, Shubham Tulsiani SIGGRAPH Asia, 2026 paper / project page / code
	SAM 3D Body: Robust Full-Body Human Mesh Recovery Xitong Yang, Devansh Kukreja, Don Pinkus, Anushka Sagar, Taosha Fan, Jinhyung Park, Soyong Shin, Jinkun Cao, Jiawei Liu, Nicolas Ugrinovic, Matt Feiszli, Jitendra Malik, Piotr Dollar, Kris Kitani Computer Vision and Pattern Recognition (CVPR), 2026 (Award Nominee) paper / project page / code
	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 paper / project page / code / bibtex
	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 paper / project page / code / bibtex
	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) paper / project page / code / bibtex
	Permutation-Invariant Relational Network for Multi-person 3D Pose Estimation Nicolas Ugrinovic, Adria Ruiz, Antonio Agudo, Alberto Sanfeliu, Francesc Moreno-Noguer Int. Conf. on Computer Vision Theory and Applications (VISAPP), 2022 paper
	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) paper / bibtex

Academic Services

Serve as reviewer for ECCV, CVPR, ICRA, NeurIPS, ICLR, 3DV

Taken from Jon Barron's website.