activity
20242026
collaborators

7 papers

cs.CV2026

Polyglot: Multilingual Style Preserving Speech-Driven Facial Animation

Federico Nocentini, Kwanggyoon Seo, Qingju Liu +6

Speech-Driven Facial Animation (SDFA) has gained significant attention due to its applications in movies, video games, and virtual reality. However, most existing models are traine…

cs.CV2026

FreeTalk: Emotional Topology-Free 3D Talking Heads

Federico Nocentini, Thomas Besnier, Claudio Ferrari +2

Speech-driven 3D facial animation has advanced rapidly, yet most approaches remain tied to registered template meshes, preventing effective deployment on raw 3D scans with arbitrar…

cs.CV2026

Revisiting Emotions Representation for Recognition in the Wild

Joao Baptista Cardia Neto, Claudio Ferrari, Stefano Berretti

Facial emotion recognition has been typically cast as a single-label classification problem of one out of six prototypical emotions. However, that is an oversimplification that is…

cs.CV2026

Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads

Federico Nocentini, Thomas Besnier, Claudio Ferrari +3

Generating speech-driven 3D talking heads presents numerous challenges; among those is dealing with varying mesh topologies where no point-wise correspondence exists across the mes…

cs.CV2025

EmoVOCA: Speech-Driven Emotional 3D Talking Heads

Federico Nocentini, Claudio Ferrari, Stefano Berretti

The domain of 3D talking head generation has witnessed significant progress in recent years. A notable challenge in this field consists in blending speech-related motions with expr…

cs.CV2025

3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method Evaluation

Evangelos Sariyanidi, Claudio Ferrari, Federico Nocentini +3

Computing the standard benchmark metric for 3D face reconstruction, namely geometric error, requires a number of steps, such as mesh cropping, rigid alignment, or point corresponde…