I am Federico Nocentini, I am now a postdoctoral researcher at Trinity College Dublin, under the supervision of Prof. Binh-Son Hua.

I recently obtained my PhD from the University of Florence at the Media Integration and Communication Center (MICC), under the supervision of Prof. Stefano Berretti and Prof. Claudio Ferrari.

I was a research scientist intern at Flawless AI, where I focused on multilingual speech-driven facial animation under the supervision of Akin Caliskan.

My main research interest revolve around 3D Computer Vision and Deep Learning, with a particular focus on human analysis applications, 3D and 4D generative face models.

Previously, I obtained my MSc in Computer Science and Engineering at the University of Florence under the supervision of Prof. Stefano Berretti and Prof. Claudio Ferrari with a thesis titled “Generating Emotional 3D Talking Heads from Audio Spectrograms.”

If you wish to learn more about my research or explore potential collaborations, please feel free to reach out via email!

Publications

• Polyglot: Multilingual Style Preserving Speech-Driven Facial Animation
  Federico Nocentini, Kwanggyoon Seo, Qingju Liu, Claudio Ferrari, Stefano Berretti, David Ferman, Hyeongwoo Kim, Pablo Garrido, Akin Caliskan
  IEEE International Conference on Automatic Face and Gesture Recognition (FG 2026), Oral

• Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads
  Federico Nocentini, Thomas Besnier, Claudio Ferrari, Sylvain Arguillere, Mohamed Daoudi, Stefano Berretti
  International Journal of Computer Vision (IJCV 2026)

• 3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation
  Evangelos Sariyanidi, Claudio Ferrari, Federico Nocentini, Stefano Berretti, Andrea Cavallaro, Birkan Tunc
  IEEE International Conference on Automatic Face and Gesture Recognition (FG 2025), Oral

• EmoVOCA: Speech-Driven Emotional 3D Talking Heads
  Federico Nocentini, Claudio Ferrari, Stefano Berretti
  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025)

• ScanTalk: 3D Talking Heads from Unregistered Scans
  Federico Nocentini, Thomas Besnier, Claudio Ferrari, Sylvain Arguillere, Stefano Berretti, Mohamed Daoudi
  European Conference on Computer Vision (ECCV 2024)

• Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation
  Federico Nocentini, Claudio Ferrari, Stefano Berretti
  International Conference on Image Analysis and Processing (ICIAP 2023), Oral

Latest News

• I successfully defended my PhD thesis, 3D Talking Heads: Advancing Realism and Generalization, in April 2026.

• Our paper Polyglot: Multilingual Style Preserving Speech-Driven Facial Animation has been accepted at FG 2026 in Kyoto.

• Our paper Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads has been accepted for publication at IJCV.

• Our paper 3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation has been accepted at FG 2025.

• Our paper EmoVOCA: Speech-Driven Emotional 3D Talking Heads has been accepted at WACV 2025.

• I presented our Demo EmoVOCA: Speech-Driven Emotional 3D Talking Heads at ECCV 2024.

• Our paper ScanTalk: 3D Talking Heads from Unregistered Scans has been accepted at ECCV 2024.

• Our demo S2L+S2D: Identity-Preserving Speech-Driven 3D Talking Heads has received the Best Demo Award at IJCB 2023.

• Our paper Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation has been accepted at ICIAP 2023.