arXiv subjects

Stefano Berretti

Publications and source records attributed to Stefano Berretti.

At least 19 recordsLinked to original sources

arXiv2026

Polyglot: Multilingual Style Preserving Speech-Driven Facial Animation

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 trained on single-language data, limiting their effectiveness in real-world multilingual scenarios. In this work, we address multilingual SDFA, which is essential for realistic generation since language influences phonetics, rhythm, intonation, and facial expressions. Speaking style is also shaped by individual differences, not only by language. Existing methods typically rely on either language-specific or speaker-specific conditioning, but not both, limiting their ability to model their interaction. We introduce Polyglot, a unified diffusion-based architecture for personalized multilingual SDFA. Our method uses transcript embeddings to encode language information and style embeddings extracted from reference facial sequences to capture individual speaking characteristics. Polyglot does not require predefined language or speaker labels, enabling generalization across languages and speakers through self-supervised learning. By jointly conditioning on language and style, it captures expressive traits such as rhythm, articulation, and habitual facial movements, producing temporally coherent and realistic animations. Experiments show improved performance in both monolingual and multilingual settings, providing a unified framework for modeling language and personal style in SDFA.

cs.CV↗

arXiv2026

SEDTalker: Emotion-Aware 3D Facial Animation Using Frame-Level Speech Emotion Diarization

We introduce SEDTalker, an emotion-aware framework for speech-driven 3D facial animation that leverages frame-level speech emotion diarization to achieve fine-grained expressive control. Unlike prior approaches that rely on utterance-level or manually specified emotion labels, our method predicts temporally dense emotion categories and intensities directly from speech, enabling continuous modulation of facial expressions over time. The diarized emotion signals are encoded as learned embeddings and used to condition a speech-driven 3D animation model based on a hybrid Transformer-Mamba architecture. This design allows effective disentanglement of linguistic content and emotional style while preserving identity and temporal coherence. We evaluate our approach on a large-scale multi-corpus dataset for speech emotion diarization and on the EmoVOCA dataset for emotional 3D facial animation. Quantitative results demonstrate strong frame-level emotion recognition performance and low geometric and temporal reconstruction errors, while qualitative results show smooth emotion transitions and consistent expression control. These findings highlight the effectiveness of frame-level emotion diarization for expressive and controllable 3D talking head generation.

cs.CV↗

arXiv2026

FreeTalk: Emotional Topology-Free 3D Talking Heads

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 arbitrary topology. At the same time, modeling controllable emotional dynamics beyond lip articulation remains challenging, and is often tied to template-based parameterizations. We address these challenges by proposing FreeTalk, a two-stage framework for emotion-conditioned 3D talking-head animation that generalizes to unregistered face meshes with arbitrary vertex count and connectivity. First, Audio-To-Sparse (ATS) predicts a temporally coherent sequence of 3D landmark displacements from speech audio, conditioned on an emotion category and intensity. This sparse representation captures both articulatory and affective motion while remaining independent of mesh topology. Second, Sparse-To-Mesh (STM) transfers the predicted landmark motion to a target mesh by combining intrinsic surface features with landmark-to-vertex conditioning, producing dense per-vertex deformations without template fitting or correspondence supervision at test time. Extensive experiments show that FreeTalk matches specialized baselines when trained in-domain, while providing substantially improved robustness to unseen identities and mesh topologies. Code and pre-trained models will be made publicly available.

cs.CV↗

arXiv2026

Revisiting Emotions Representation for Recognition in the Wild

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 unsuitable for representing the multifaceted spectrum of spontaneous emotional states, which are most often the result of a combination of multiple emotions contributing at different intensities. Building on this, a promising direction that was explored recently is to cast emotion recognition as a distribution learning problem. Still, such approaches are limited in that research datasets are typically annotated with a single emotion class. In this paper, we contribute a novel approach to describe complex emotional states as probability distributions over a set of emotion classes. To do so, we propose a solution to automatically re-label existing datasets by exploiting the result of a study in which a large set of both basic and compound emotions is mapped to probability distributions in the Valence-Arousal-Dominance (VAD) space. In this way, given a face image annotated with VAD values, we can estimate the likelihood of it belonging to each of the distributions, so that emotional states can be described as a mixture of emotions, enriching their description, while also accounting for the ambiguous nature of their perception. In a preliminary set of experiments, we illustrate the advantages of this solution and a new possible direction of investigation. Data annotations are available at https://github.com/jbcnrlz/affectnet-b-annotation.

cs.CV↗

arXiv2025

No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts

Diffusion models have recently advanced human motion generation, producing realistic and diverse animations from textual prompts. However, adapting these models to unseen actions or styles typically requires additional motion capture data and full retraining, which is costly and difficult to scale. We propose a post-training framework based on Reinforcement Learning that fine-tunes pretrained motion diffusion models using only textual prompts, without requiring any motion ground truth. Our approach employs a pretrained text-motion retrieval network as a reward signal and optimizes the diffusion policy with Denoising Diffusion Policy Optimization, effectively shifting the model's generative distribution toward the target domain without relying on paired motion data. We evaluate our method on cross-dataset adaptation and leave-one-out motion experiments using the HumanML3D and KIT-ML datasets across both latent- and joint-space diffusion architectures. Results from quantitative metrics and user studies show that our approach consistently improves the quality and diversity of generated motions, while preserving performance on the original distribution. Our approach is a flexible, data-efficient, and privacy-preserving solution for motion adaptation.

cs.CV↗

arXiv2025

SHREC'25 Track on Multiple Relief Patterns: Report and Analysis

This SHREC 2025 track focuses on the recognition and segmentation of relief patterns embedded on the surface of a set of synthetically generated triangle meshes. We report the methods proposed by the participants, whose performance highlights the inherent complexity of solving the problem, which is still open. Then, we discuss the critical aspects of the proposed tasks, highlight the limitations of current techniques, and outline possible directions for future research. All resources and track details are available at the official track webpage: https://sites.google.com/unifi.it/shrec25-relief-pattern.

cs.CG↗

arXiv2025

A Standardized Benchmark for Skeleton-Based Rehabilitation Assessment Using Deep Learning

Automated assessment of human motion plays a vital role in rehabilitation, enabling objective evaluation of patient performance and progress. Unlike general human activity recognition, rehabilitation motion assessment focuses on analyzing the quality of movement within the same action class, requiring the detection of subtle deviations from ideal motion. Recent advances in deep learning and video-based skeleton extraction have opened new possibilities for accessible, scalable motion assessment using affordable devices such as smartphones or webcams. However, the field lacks standardized benchmarks, consistent evaluation protocols, and reproducible methodologies, limiting progress and comparability across studies. In this work, we address these gaps by (i) aggregating existing rehabilitation datasets into a unified archive called Rehab-Pile, (ii) proposing a general benchmarking framework for evaluating deep learning methods in this domain, and (iii) conducting extensive benchmarking of multiple architectures across classification and regression tasks. All datasets and implementations are released to the community to support transparency and reproducibility. This paper aims to establish a solid foundation for future research in automated rehabilitation assessment and foster the development of reliable, accessible, and personalized rehabilitation solutions. The datasets, source-code and results of this article are all publicly available.

cs.CV↗

arXiv2025

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

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 correspondence. Current benchmark tools are monolithic (they implement a specific combination of these steps), even though there is no consensus on the best way to measure error. 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. Furthermore, we propose a new component, namely correction, and present a computationally efficient approach that penalizes for mesh topology inconsistency. Using this toolkit, we test 16 error estimators with 10 reconstruction methods on two real and two synthetic datasets. Critically, the widely used ICP-based estimator provides the worst benchmarking performance, as it significantly alters the true ranking of the top-5 reconstruction methods. Notably, the correlation of ICP with the true error can be as low as 0.41. Moreover, non-rigid alignment leads to significant improvement (correlation larger than 0.90), highlighting the importance of annotating 3D landmarks on datasets. Finally, the proposed correction scheme, together with non-rigid warping, leads to an accuracy on a par with the best non-rigid ICP-based estimators, but runs an order of magnitude faster. Our open-source codebase is designed for researchers to easily compare alternatives for each component, thus helping accelerating progress in benchmarking for 3D face reconstruction and, furthermore, supporting the improvement of learned reconstruction methods, which depend on accurate error estimation for effective training.

cs.CV↗

arXiv2025

Look Into the LITE in Deep Learning for Time Series Classification

Deep learning models have been shown to be a powerful solution for Time Series Classification (TSC). State-of-the-art architectures, while producing promising results on the UCR and the UEA archives , present a high number of trainable parameters. This can lead to long training with high CO2 emission, power consumption and possible increase in the number of FLoating-point Operation Per Second (FLOPS). In this paper, we present a new architecture for TSC, the Light Inception with boosTing tEchnique (LITE) with only 2.34% of the number of parameters of the state-of-the-art InceptionTime model, while preserving performance. This architecture, with only 9, 814 trainable parameters due to the usage of DepthWise Separable Convolutions (DWSC), is boosted by three techniques: multiplexing, custom filters, and dilated convolution. The LITE architecture, trained on the UCR, is 2.78 times faster than InceptionTime and consumes 2.79 times less CO2 and power. To evaluate the performance of the proposed architecture on multivariate time series data, we adapt LITE to handle multivariate time series, we call this version LITEMV. To bring theory into application, we also conducted experiments using LITEMV on multivariate time series representing human rehabilitation movements, showing that LITEMV not only is the most efficient model but also the best performing for this application on the Kimore dataset, a skeleton based human rehabilitation exercises dataset. Moreover, to address the interpretability of LITEMV, we present a study using Class Activation Maps to understand the classification decision taken by the model during evaluation.

cs.LG↗

arXiv2024

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

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 meshes the model can animate. While previous literature works assume fixed mesh structures, in this work we present the first framework capable of animating 3D faces in arbitrary topologies, including real scanned data. Our approach leverages heat diffusion to predict features that are robust to the mesh topology. We explore two training settings: a registered one, in which meshes in a training sequences share a fixed topology but any mesh can be animated at test time, and an fully unregistered 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. An extensive evaluation shows our approach performs favorably compared to fixed topology techniques, setting a new benchmark by offering a versatile and high-fidelity solution for 3D talking heads where the topology constraint is dropped. The code along with the pre-trained model are available.

cs.CV↗

arXiv2024

ScanTalk: 3D Talking Heads from Unregistered Scans

Speech-driven 3D talking heads generation has emerged as a significant area of interest among researchers, presenting numerous challenges. Existing methods are constrained by animating faces with fixed topologies, wherein point-wise correspondence is established, and the number and order of points remains consistent across all identities the model can animate. In this work, we present \textbf{ScanTalk}, a novel framework capable of animating 3D faces in arbitrary topologies including scanned data. Our approach relies on the DiffusionNet architecture to overcome the fixed topology constraint, offering promising avenues for more flexible and realistic 3D animations. By leveraging the power of DiffusionNet, ScanTalk not only adapts to diverse facial structures but also maintains fidelity when dealing with scanned data, thereby enhancing the authenticity and versatility of generated 3D talking heads. Through comprehensive comparisons with state-of-the-art methods, we validate the efficacy of our approach, demonstrating its capacity to generate realistic talking heads comparable to existing techniques. While our primary objective is to develop a generic method free from topological constraints, all state-of-the-art methodologies are bound by such limitations. Code for reproducing our results, and the pre-trained model are available at https://github.com/miccunifi/ScanTalk .

cs.CV↗

arXiv2024

Generation of Complex 3D Human Motion by Temporal and Spatial Composition of Diffusion Models

In this paper, we address the challenge of generating realistic 3D human motions for action classes that were never seen during the training phase. Our approach involves decomposing complex actions into simpler movements, specifically those observed during training, by leveraging the knowledge of human motion contained in GPTs models. These simpler movements are then combined into a single, realistic animation using the properties of diffusion models. Our claim is that this decomposition and subsequent recombination of simple movements can synthesize an animation that accurately represents the complex input action. This method operates during the inference phase and can be integrated with any pre-trained diffusion model, enabling the synthesis of motion classes not present in the training data. We evaluate our method by dividing two benchmark human motion datasets into basic and complex actions, and then compare its performance against the state-of-the-art.

cs.CV↗

arXiv2024

JambaTalk: Speech-Driven 3D Talking Head Generation Based on Hybrid Transformer-Mamba Model

In recent years, the talking head generation has become a focal point for researchers. Considerable effort is being made to refine lip-sync motion, capture expressive facial expressions, generate natural head poses, and achieve high-quality video. However, no single model has yet achieved equivalence across all quantitative and qualitative metrics. We introduce Jamba, a hybrid Transformer-Mamba model, to animate a 3D face. Mamba, a pioneering Structured State Space Model (SSM) architecture, was developed to overcome the limitations of conventional Transformer architectures, particularly in handling long sequences. This challenge has constrained traditional models. Jamba combines the advantages of both the Transformer and Mamba approaches, offering a comprehensive solution. Based on the foundational Jamba block, we present JambaTalk to enhance motion variety and lip sync through multimodal integration. Extensive experiments reveal that our method achieves performance comparable or superior to state-of-the-art models.

cs.CV↗

arXiv2024

Establishing a Unified Evaluation Framework for Human Motion Generation: A Comparative Analysis of Metrics

The development of generative artificial intelligence for human motion generation has expanded rapidly, necessitating a unified evaluation framework. This paper presents a detailed review of eight evaluation metrics for human motion generation, highlighting their unique features and shortcomings. We propose standardized practices through a unified evaluation setup to facilitate consistent model comparisons. Additionally, we introduce a novel metric that assesses diversity in temporal distortion by analyzing warping diversity, thereby enhancing the evaluation of temporal data. We also conduct experimental analyses of three generative models using a publicly available dataset, offering insights into the interpretation of each metric in specific case scenarios. Our goal is to offer a clear, user-friendly evaluation framework for newcomers, complemented by publicly accessible code.

cs.CV↗

arXiv2024

EmoVOCA: Speech-Driven Emotional 3D Talking Heads

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 expression dynamics, which is primarily caused by the lack of comprehensive 3D datasets that combine diversity in spoken sentences with a variety of facial expressions. Whereas literature works attempted to exploit 2D video data and parametric 3D models as a workaround, these still show limitations when jointly modeling the two motions. In this work, we address this problem from a different perspective, and propose an innovative data-driven technique that we used for creating a synthetic dataset, called EmoVOCA, obtained by combining a collection of inexpressive 3D talking heads and a set of 3D expressive sequences. To demonstrate the advantages of this approach, and the quality of the dataset, we then designed and trained an emotional 3D talking head generator that accepts a 3D face, an audio file, an emotion label, and an intensity value as inputs, and learns to animate the audio-synchronized lip movements with expressive traits of the face. Comprehensive experiments, both quantitative and qualitative, using our data and generator evidence superior ability in synthesizing convincing animations, when compared with the best performing methods in the literature. Our code and pre-trained model will be made available.

cs.CV↗

arXiv2024

Finding Foundation Models for Time Series Classification with a PreText Task

Over the past decade, Time Series Classification (TSC) has gained an increasing attention. While various methods were explored, deep learning - particularly through Convolutional Neural Networks (CNNs)-stands out as an effective approach. However, due to the limited availability of training data, defining a foundation model for TSC that overcomes the overfitting problem is still a challenging task. The UCR archive, encompassing a wide spectrum of datasets ranging from motion recognition to ECG-based heart disease detection, serves as a prime example for exploring this issue in diverse TSC scenarios. In this paper, we address the overfitting challenge by introducing pre-trained domain foundation models. A key aspect of our methodology is a novel pretext task that spans multiple datasets. This task is designed to identify the originating dataset of each time series sample, with the goal of creating flexible convolution filters that can be applied across different datasets. The research process consists of two phases: a pre-training phase where the model acquires general features through the pretext task, and a subsequent fine-tuning phase for specific dataset classifications. Our extensive experiments on the UCR archive demonstrate that this pre-training strategy significantly outperforms the conventional training approach without pre-training. This strategy effectively reduces overfitting in small datasets and provides an efficient route for adapting these models to new datasets, thus advancing the capabilities of deep learning in TSC.

cs.LG↗

arXiv2023

ShapeDBA: Generating Effective Time Series Prototypes using ShapeDTW Barycenter Averaging

Time series data can be found in almost every domain, ranging from the medical field to manufacturing and wireless communication. Generating realistic and useful exemplars and prototypes is a fundamental data analysis task. In this paper, we investigate a novel approach to generating realistic and useful exemplars and prototypes for time series data. Our approach uses a new form of time series average, the ShapeDTW Barycentric Average. We therefore turn our attention to accurately generating time series prototypes with a novel approach. The existing time series prototyping approaches rely on the Dynamic Time Warping (DTW) similarity measure such as DTW Barycentering Average (DBA) and SoftDBA. These last approaches suffer from a common problem of generating out-of-distribution artifacts in their prototypes. This is mostly caused by the DTW variant used and its incapability of detecting neighborhood similarities, instead it detects absolute similarities. Our proposed method, ShapeDBA, uses the ShapeDTW variant of DTW, that overcomes this issue. We chose time series clustering, a popular form of time series analysis to evaluate the outcome of ShapeDBA compared to the other prototyping approaches. Coupled with the k-means clustering algorithm, and evaluated on a total of 123 datasets from the UCR archive, our proposed averaging approach is able to achieve new state-of-the-art results in terms of Adjusted Rand Index.

cs.LG↗

arXiv2023

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

This paper presents a novel approach for generating 3D talking heads from raw audio inputs. Our 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. The underlying musculoskeletal structure then allows us to learn how their motion influences the geometrical deformations of the whole face. The proposed method employs two distinct models to this aim: the first one learns to generate the motion of a sparse set of landmarks from the given audio. The second model expands such landmarks motion to a dense motion field, which is utilized to animate a given 3D mesh in neutral state. Additionally, we introduce a novel loss function, named Cosine Loss, which minimizes the angle between the generated motion vectors and the ground truth ones. Using landmarks in 3D talking head generation offers various advantages such as consistency, reliability, and obviating the need for manual-annotation. Our approach is designed to be identity-agnostic, enabling high-quality facial animations for any users without additional data or training.

cs.CV↗