Panagiotis P. Filntisis

Panagiotis P. Filntisis, George Retsinas, Foivos Paraperas-Papantoniou et al.

The recent state of the art on monocular 3D face reconstruction from image data has made some impressive advancements, thanks to the advent of Deep Learning. However, it has mostly focused on input coming from a single RGB image, overlooking the following important factors: a) Nowadays, the vast majority of facial image data of interest do not originate from single images but rather from videos, which contain rich dynamic information. b) Furthermore, these videos typically capture individuals in some form of verbal communication (public talks, teleconferences, audiovisual human-computer interactions, interviews, monologues/dialogues in movies, etc). When existing 3D face reconstruction methods are applied in such videos, the artifacts in the reconstruction of the shape and motion of the mouth area are often severe, since they do not match well with the speech audio. To overcome the aforementioned limitations, we present the first method for visual speech-aware perceptual reconstruction of 3D mouth expressions. We do this by proposing a "lipread" loss, which guides the fitting process so that the elicited perception from the 3D reconstructed talking head resembles that of the original video footage. We demonstrate that, interestingly, the lipread loss is better suited for 3D reconstruction of mouth movements compared to traditional landmark losses, and even direct 3D supervision. Furthermore, the devised method does not rely on any text transcriptions or corresponding audio, rendering it ideal for training in unlabeled datasets. We verify the efficiency of our method through exhaustive objective evaluations on three large-scale datasets, as well as subjective evaluation with two web-based user studies.

Christina O. Tze, Panagiotis P. Filntisis, Athanasia-Lida Dimou et al.

In this paper, we introduce a neural rendering pipeline for transferring the facial expressions, head pose, and body movements of one person in a source video to another in a target video. We apply our method to the challenging case of Sign Language videos: given a source video of a sign language user, we can faithfully transfer the performed manual (e.g., handshape, palm orientation, movement, location) and non-manual (e.g., eye gaze, facial expressions, mouth patterns, head, and body movements) signs to a target video in a photo-realistic manner. Our method can be used for Sign Language Anonymization, Sign Language Production (synthesis module), as well as for reenacting other types of full body activities (dancing, acting performance, exercising, etc.). We conduct detailed qualitative and quantitative evaluations and comparisons, which demonstrate the particularly promising and realistic results that we obtain and the advantages of our method over existing approaches.

Ioannis Pikoulis, Panagiotis P. Filntisis, Petros Maragos

In this paper, we investigate the emotion manipulation capabilities of diffusion models with "in-the-wild" images, a rather unexplored application area relative to the vast and rapidly growing literature for image-to-image translation tasks. Our proposed method encapsulates several pieces of prior work, with the most important being Latent Diffusion models and text-driven manipulation with CLIP latents. We conduct extensive qualitative and quantitative evaluations on AffectNet, demonstrating the superiority of our approach in terms of image quality and realism, while achieving competitive results relative to emotion translation compared to a variety of GAN-based counterparts. Code is released as a publicly available repo.

Nikolaos Kegkeroglou, Panagiotis P. Filntisis, Petros Maragos

The COVID-19 pandemic has undoubtedly changed the standards and affected all aspects of our lives, especially social communication. It has forced people to extensively wear medical face masks, in order to prevent transmission. This face occlusion can strongly irritate emotional reading from the face and urges us to incorporate the whole body as an emotional cue. In this paper, we conduct insightful studies about the effect of face occlusion on emotion recognition performance, and showcase the superiority of full body input over the plain masked face. We utilize a deep learning model based on the Temporal Segment Network framework, and aspire to fully overcome the face mask consequences. Although facial and bodily features can be learned from a single input, this may lead to irrelevant information confusion. By processing those features separately and fusing their prediction scores, we are more effectively taking advantage of both modalities. This framework also naturally supports temporal modeling, by mingling information among neighboring frames. In combination, these techniques form an effective system capable of tackling emotion recognition difficulties, caused by safety protocols applied in crucial areas.

Panagiotis P. Filntisis, George Retsinas, Radek Daněček et al.

Recent frameworks like ToFu and TEMPEH provide an automated alternative to classical registration pipelines by predicting 3D meshes in dense semantic correspondence directly from calibrated multi-view images. However, these learning-based methods rely on the slow, manual registration pipelines they aim to replace for their training supervision. We overcome this limitation with MOCHI (Multi-view Optimizable Correspondence of Heads from Images), a multi-view 3D face prediction framework trained without requiring registered training data. MOCHI eliminates the registration data dependency by enforcing topological consistency through a pseudo-linear inverse kinematic solver. Semantic alignment is guided by dense keypoints from a 2D landmark predictor trained exclusively on synthetic data. Our analysis further reveals that standard point-to-surface distances induce training instabilities and visual artifacts in registration-free settings. We propose pointmap- and normal-based losses instead, which provide smoother gradients and superior reconstruction fidelity. Finally, we introduce a test-time optimization scheme that refines network weights over a few dozen iterations. This approach bridges the gap between feed-forward efficiency and iterative optimization precision, allowing MOCHI to outperform traditional labor-intensive pipelines in both reconstruction accuracy and visual quality. Code and model are public at: https://filby89.github.io/mochi.

Vasiliki Vasileiou, Panagiotis P. Filntisis, Petros Maragos et al.

Monocular head pose estimation is traditionally formulated as direct regression from a single image to an absolute pose. This paradigm forces the network to implicitly internalize a dataset-specific canonical reference frame. In this work, we argue that predicting the relative rigid transformation between two observed head configurations is a fundamentally easier and more robust formulation. We introduce VGGT-HPE, a relative head pose estimator built upon a general-purpose geometry foundation model. Finetuned exclusively on synthetic facial renderings, our method sidesteps the need for an implicit anchor by reducing the problem to estimating a geometric displacement from an explicitly provided anchor with a known pose. As a practical benefit, the relative formulation also allows the anchor to be chosen at test time - for instance, a near-neutral frame or a temporally adjacent one - so that the prediction difficulty can be controlled by the application. Despite zero real-world training data, VGGT-HPE achieves state-of-the-art results on the BIWI benchmark, outperforming established absolute regression methods trained on mixed and real datasets. Through controlled easy- and hard-pair benchmarks, we also systematically validate our core hypothesis: relative prediction is intrinsically more accurate than absolute regression, with the advantage scaling alongside the difficulty of the target pose. Project page and code: https://vasilikivas.github.io/VGGT-HPE

Nikolaos Tsalkitzis, Panagiotis P. Filntisis, Petros Maragos et al.

Digital phenotyping enables continuous passive monitoring of behavior and physiology, offering a promising paradigm for early detection of psychotic relapse. In this work, we develop and systematically study two smartwatch-based frameworks for daily relapse detection. The first forecasts cardiac dynamics and flags deviations between predicted and observed features as indicators of abnormality. The second adopts a multi-task formulation that fuses sleep with motion and cardiac-derived signals, learning time-aware embeddings and predicting measurement timing. Both pipelines use Transformer encoders and output a daily anomaly score, derived from predictive uncertainty estimated via an ensemble of multilayer perceptrons to improve robustness to real-world wearable variability. While each framework independently demonstrates strong predictive power, we show that they capture complementary physiological signatures. Consequently, we propose a late-fusion strategy that synergistically combines the anomaly signals from both architectures into a unified decision score. We benchmark our methodology on the 2nd e-Prevention Grand Challenge dataset, where our fused model achieves a 8% relative improvement over the competition-winning baseline. Our results, supported by extensive ablation studies, suggest that the integration of diverse digital phenotypes, cardiac, motion, and sleep, is essential for the high-fidelity detection of psychotic relapse in real-world settings.

George Retsinas, Panagiotis P. Filntisis, Radek Danecek et al.

While existing methods for 3D face reconstruction from in-the-wild images excel at recovering the overall face shape, they commonly miss subtle, extreme, asymmetric, or rarely observed expressions. We improve upon these methods with SMIRK (Spatial Modeling for Image-based Reconstruction of Kinesics), which faithfully reconstructs expressive 3D faces from images. We identify two key limitations in existing methods: shortcomings in their self-supervised training formulation, and a lack of expression diversity in the training images. For training, most methods employ differentiable rendering to compare a predicted face mesh with the input image, along with a plethora of additional loss functions. This differentiable rendering loss not only has to provide supervision to optimize for 3D face geometry, camera, albedo, and lighting, which is an ill-posed optimization problem, but the domain gap between rendering and input image further hinders the learning process. Instead, SMIRK replaces the differentiable rendering with a neural rendering module that, given the rendered predicted mesh geometry, and sparsely sampled pixels of the input image, generates a face image. As the neural rendering gets color information from sampled image pixels, supervising with neural rendering-based reconstruction loss can focus solely on the geometry. Further, it enables us to generate images of the input identity with varying expressions while training. These are then utilized as input to the reconstruction model and used as supervision with ground truth geometry. This effectively augments the training data and enhances the generalization for diverse expressions. Our qualitative, quantitative and particularly our perceptual evaluations demonstrate that SMIRK achieves the new state-of-the art performance on accurate expression reconstruction. Project webpage: https://georgeretsi.github.io/smirk/.

Georgios Milis, Panagiotis P. Filntisis, Anastasios Roussos et al.

Recent advances in deep learning for sequential data have given rise to fast and powerful models that produce realistic videos of talking humans. The state of the art in talking face generation focuses mainly on lip-syncing, being conditioned on audio clips. However, having the ability to synthesize talking humans from text transcriptions rather than audio is particularly beneficial for many applications and is expected to receive more and more attention, following the recent breakthroughs in large language models. For that, most methods implement a cascaded 2-stage architecture of a text-to-speech module followed by an audio-driven talking face generator, but this ignores the highly complex interplay between audio and visual streams that occurs during speaking. In this paper, we propose the first, to the best of our knowledge, text-driven audiovisual speech synthesizer that uses Transformers and does not follow a cascaded approach. Our method, which we call NEUral Text to ARticulate Talk (NEUTART), is a talking face generator that uses a joint audiovisual feature space, as well as speech-informed 3D facial reconstructions and a lip-reading loss for visual supervision. The proposed model produces photorealistic talking face videos with human-like articulation and well-synced audiovisual streams. Our experiments on audiovisual datasets as well as in-the-wild videos reveal state-of-the-art generation quality both in terms of objective metrics and human evaluation.

Marios Glytsos, Panagiotis P. Filntisis, George Retsinas et al.

Accurate 6D object pose estimation is essential for robotic grasping and manipulation, particularly in agriculture, where fruits and vegetables exhibit high intra-class variability in shape, size, and texture. The vast majority of existing methods rely on instance-specific CAD models or require depth sensors to resolve geometric ambiguities, making them impractical for real-world agricultural applications. In this work, we introduce PLANTPose, a novel framework for category-level 6D pose estimation that operates purely on RGB input. PLANTPose predicts both the 6D pose and deformation parameters relative to a base mesh, allowing a single category-level CAD model to adapt to unseen instances. This enables accurate pose estimation across varying shapes without relying on instance-specific data. To enhance realism and improve generalization, we also leverage Stable Diffusion to refine synthetic training images with realistic texturing, mimicking variations due to ripeness and environmental factors and bridging the domain gap between synthetic data and the real world. Our evaluations on a challenging benchmark that includes bananas of various shapes, sizes, and ripeness status demonstrate the effectiveness of our framework in handling large intraclass variations while maintaining accurate 6D pose predictions, significantly outperforming the state-of-the-art RGB-based approach MegaPose.

Nikos Giannakakis, Argyris Manetas, Panagiotis P. Filntisis et al.

Learning visual representations from observing actions to benefit robot visuo-motor policy generation is a promising direction that closely resembles human cognitive function and perception. Motivated by this, and further inspired by psychological theories suggesting that humans process scenes in an object-based fashion, we propose an object-centric encoder that performs semantic segmentation and visual representation generation in a coupled manner, unlike other works, which treat these as separate processes. To achieve this, we leverage the Slot Attention mechanism and use the SOLV model, pretrained in large out-of-domain datasets, to bootstrap fine-tuning on human action video data. Through simulated robotic tasks, we demonstrate that visual representations can enhance reinforcement and imitation learning training, highlighting the effectiveness of our integrated approach for semantic segmentation and encoding. Furthermore, we show that exploiting models pretrained on out-of-domain datasets can benefit this process, and that fine-tuning on datasets depicting human actions -- although still out-of-domain -- , can significantly improve performance due to close alignment with robotic tasks. These findings show the capability to reduce reliance on annotated or robot-specific action datasets and the potential to build on existing visual encoders to accelerate training and improve generalizability.

Foivos Paraperas Papantoniou, Panagiotis P. Filntisis, Petros Maragos et al.

In this paper, we introduce a novel deep learning method for photo-realistic manipulation of the emotional state of actors in "in-the-wild" videos. The proposed method is based on a parametric 3D face representation of the actor in the input scene that offers a reliable disentanglement of the facial identity from the head pose and facial expressions. It then uses a novel deep domain translation framework that alters the facial expressions in a consistent and plausible manner, taking into account their dynamics. Finally, the altered facial expressions are used to photo-realistically manipulate the facial region in the input scene based on an especially-designed neural face renderer. To the best of our knowledge, our method is the first to be capable of controlling the actor's facial expressions by even using as a sole input the semantic labels of the manipulated emotions, while at the same time preserving the speech-related lip movements. We conduct extensive qualitative and quantitative evaluations and comparisons, which demonstrate the effectiveness of our approach and the especially promising results that we obtain. Our method opens a plethora of new possibilities for useful applications of neural rendering technologies, ranging from movie post-production and video games to photo-realistic affective avatars.

Panagiotis Antoniadis, Ioannis Pikoulis, Panagiotis P. Filntisis et al.

In this work we tackle the task of video-based audio-visual emotion recognition, within the premises of the 2nd Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW2). Poor illumination conditions, head/body orientation and low image resolution constitute factors that can potentially hinder performance in case of methodologies that solely rely on the extraction and analysis of facial features. In order to alleviate this problem, we leverage both bodily and contextual features, as part of a broader emotion recognition framework. We choose to use a standard CNN-RNN cascade as the backbone of our proposed model for sequence-to-sequence (seq2seq) learning. Apart from learning through the RGB input modality, we construct an aural stream which operates on sequences of extracted mel-spectrograms. Our extensive experiments on the challenging and newly assembled Aff-Wild2 dataset verify the validity of our intuitive multi-stream and multi-modal approach towards emotion recognition in-the-wild. Emphasis is being laid on the the beneficial influence of the human body and scene context, as aspects of the emotion recognition process that have been left relatively unexplored up to this point. All the code was implemented using PyTorch and is publicly available.

Panagiotis Antoniadis, Panagiotis P. Filntisis, Petros Maragos

Over the past few years, deep learning methods have shown remarkable results in many face-related tasks including automatic facial expression recognition (FER) in-the-wild. Meanwhile, numerous models describing the human emotional states have been proposed by the psychology community. However, we have no clear evidence as to which representation is more appropriate and the majority of FER systems use either the categorical or the dimensional model of affect. Inspired by recent work in multi-label classification, this paper proposes a novel multi-task learning (MTL) framework that exploits the dependencies between these two models using a Graph Convolutional Network (GCN) to recognize facial expressions in-the-wild. Specifically, a shared feature representation is learned for both discrete and continuous recognition in a MTL setting. Moreover, the facial expression classifiers and the valence-arousal regressors are learned through a GCN that explicitly captures the dependencies between them. To evaluate the performance of our method under real-world conditions we perform extensive experiments on the AffectNet and Aff-Wild2 datasets. The results of our experiments show that our method is capable of improving the performance across different datasets and backbone architectures. Finally, we also surpass the previous state-of-the-art methods on the categorical model of AffectNet.

Ioannis Pikoulis, Panagiotis P. Filntisis, Petros Maragos

In this work we tackle the task of video-based visual emotion recognition in the wild. Standard methodologies that rely solely on the extraction of bodily and facial features often fall short of accurate emotion prediction in cases where the aforementioned sources of affective information are inaccessible due to head/body orientation, low resolution and poor illumination. We aspire to alleviate this problem by leveraging visual context in the form of scene characteristics and attributes, as part of a broader emotion recognition framework. Temporal Segment Networks (TSN) constitute the backbone of our proposed model. Apart from the RGB input modality, we make use of dense Optical Flow, following an intuitive multi-stream approach for a more effective encoding of motion. Furthermore, we shift our attention towards skeleton-based learning and leverage action-centric data as means of pre-training a Spatial-Temporal Graph Convolutional Network (ST-GCN) for the task of emotion recognition. Our extensive experiments on the challenging Body Language Dataset (BoLD) verify the superiority of our methods over existing approaches, while by properly incorporating all of the aforementioned modules in a network ensemble, we manage to surpass the previous best published recognition scores, by a large margin.

Niki Efthymiou, Panagiotis P. Filntisis, Petros Koutras et al.

In this paper we present an integrated robotic system capable of participating in and performing a wide range of educational and entertainment tasks, in collaboration with one or more children. The system, called ChildBot, features multimodal perception modules and multiple robotic agents that monitor the interaction environment, and can robustly coordinate complex Child-Robot Interaction use-cases. In order to validate the effectiveness of the system and its integrated modules, we have conducted multiple experiments with a total of 52 children. Our results show improved perception capabilities in comparison to our earlier works that ChildBot was based on. In addition, we have conducted a preliminary user experience study, employing some educational/entertainment tasks, that yields encouraging results regarding the technical validity of our system and initial insights on the user experience with it.

Panagiotis P. Filntisis, Niki Efthymiou, Petros Koutras et al.

In this paper we address the problem of multi-cue affect recognition in challenging scenarios such as child-robot interaction. Towards this goal we propose a method for automatic recognition of affect that leverages body expressions alongside facial ones, as opposed to traditional methods that typically focus only on the latter. Our deep-learning based method uses hierarchical multi-label annotations and multi-stage losses, can be trained both jointly and separately, and offers us computational models for both individual modalities, as well as for the whole body emotion. We evaluate our method on a challenging child-robot interaction database of emotional expressions collected by us, as well as on the GEMEP public database of acted emotions by adults, and show that the proposed method achieves significantly better results than facial-only expression baselines.