Publications

You can also find my articles on my Google Scholar profile.

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

Published in international Journal of Computer Vision (IJCV), 2025

We explore two training settings: a supervised one, in which training sequences share a fixed topology within a sequence but any mesh can be animated at test time, and an unsupervised one, which allows effective training with varying mesh structures. Additionally, we highlight the limitations of current evaluation metrics and propose new metrics for better lip-syncing evaluation between speech and facial movements.

Download Paper

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

Published in IEEE conference series on Automatic Face and Gesture Recognition (FG)(Oral), 2025

We present a toolkit for a Modularized 3D Face reconstruction Benchmark (M3DFB), where the fundamental components of error computation are segregated and interchangeable, allowing one to quantify the effect of each.

Download Paper

EmoVOCA: Speech-Driven Emotional 3D Talking Heads

Published in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

We present EmoVOCA, a novel dataset that can be used to train a model to generate emotional 3D talking heads. The proposed method is capable of generating emotional 3D talking heads based on a speech track, an intensity label, an emotion label, and an actor to animate

Download Paper

ScanTalk: 3D Talking Heads from Unregistered Scans

Published in European Conference on Computer Vision (ECCV), 2024

In this work, we present ScanTalk, a novel framework capable of animating 3D faces in arbitrary topologies including scanned data.

Download Paper

Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation

Published in International Conference on Image Analisys and Processing (ICIAP)(Oral), 2023

A novel approach for generating 3D talking heads from raw audio inputs. This method grounds on the idea that speech related movements can be comprehensively and efficiently described by the motion of a few control points located on the movable parts of the face, i.e., landmarks.

Download Paper

Federico Nocentini

Publications

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

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

EmoVOCA: Speech-Driven Emotional 3D Talking Heads

ScanTalk: 3D Talking Heads from Unregistered Scans

Learning Landmarks Motion from Speech for Speaker-Agnostic 3D Talking Heads Generation